mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-14 01:13:00 +08:00
1193 lines
72 KiB
HTML
1193 lines
72 KiB
HTML
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
|
<meta name="description" content="This trains is a Graph Attention Network (GAT) on Cora dataset"/>
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta name="twitter:title" content="Train a Graph Attention Network (GAT) on Cora dataset"/>
|
|
<meta name="twitter:description" content="This trains is a Graph Attention Network (GAT) on Cora dataset"/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/graphs/gat/experiment.html"/>
|
|
<meta property="og:title" content="Train a Graph Attention Network (GAT) on Cora dataset"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="LabML Neural Networks"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="Train a Graph Attention Network (GAT) on Cora dataset"/>
|
|
<meta property="og:description" content="This trains is a Graph Attention Network (GAT) on Cora dataset"/>
|
|
|
|
<title>Train a Graph Attention Network (GAT) on Cora dataset</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/graphs/gat/experiment.html"/>
|
|
<!-- Global site tag (gtag.js) - Google Analytics -->
|
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
|
<script>
|
|
window.dataLayer = window.dataLayer || [];
|
|
|
|
function gtag() {
|
|
dataLayer.push(arguments);
|
|
}
|
|
|
|
gtag('js', new Date());
|
|
|
|
gtag('config', 'G-4V3HC8HBLH');
|
|
</script>
|
|
</head>
|
|
<body>
|
|
<div id='container'>
|
|
<div id="background"></div>
|
|
<div class='section'>
|
|
<div class='docs'>
|
|
<p>
|
|
<a class="parent" href="/">home</a>
|
|
<a class="parent" href="../index.html">graphs</a>
|
|
<a class="parent" href="index.html">gat</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/graphs/gat/experiment.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai"
|
|
rel="nofollow">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
<h1>Train a Graph Attention Network (GAT) on Cora dataset</h1>
|
|
<p><a href="https://app.labml.ai/run/d6c636cadf3511eba2f1e707f612f95d"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
|
|
<span class="lineno">14</span>
|
|
<span class="lineno">15</span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
|
<span class="lineno">16</span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
|
<span class="lineno">18</span>
|
|
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">lab</span><span class="p">,</span> <span class="n">monit</span><span class="p">,</span> <span class="n">tracker</span><span class="p">,</span> <span class="n">experiment</span>
|
|
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">BaseConfigs</span>
|
|
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml.utils</span> <span class="kn">import</span> <span class="n">download</span>
|
|
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml_helpers.device</span> <span class="kn">import</span> <span class="n">DeviceConfigs</span>
|
|
<span class="lineno">23</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
|
<span class="lineno">24</span><span class="kn">from</span> <span class="nn">labml_nn.graphs.gat</span> <span class="kn">import</span> <span class="n">GraphAttentionLayer</span>
|
|
<span class="lineno">25</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.configs</span> <span class="kn">import</span> <span class="n">OptimizerConfigs</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<h2><a href="https://linqs.soe.ucsc.edu/data">Cora Dataset</a></h2>
|
|
<p>Cora dataset is a dataset of research papers.
|
|
For each paper we are given a binary feature vector that indicates the presence of words.
|
|
Each paper is classified into one of 7 classes.
|
|
The dataset also has the citation network.</p>
|
|
<p>The papers are the nodes of the graph and the edges are the citations.</p>
|
|
<p>The task is to classify the edges to the 7 classes with feature vectors and
|
|
citation network as input.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">28</span><span class="k">class</span> <span class="nc">CoraDataset</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<p>Labels for each node</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">43</span> <span class="n">labels</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-3'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-3'>#</a>
|
|
</div>
|
|
<p>Set of class names and an unique integer index</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">classes</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-4'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<p>Feature vectors for all nodes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">47</span> <span class="n">features</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
<p>Adjacency matrix with the edge information.
|
|
<code>adj_mat[i][j]</code> is <code>True</code> if there is an edge from <code>i</code> to <code>j</code>.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">50</span> <span class="n">adj_mat</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-6'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<p>Download the dataset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">52</span> <span class="nd">@staticmethod</span>
|
|
<span class="lineno">53</span> <span class="k">def</span> <span class="nf">_download</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">57</span> <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">'cora'</span><span class="p">)</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
|
|
<span class="lineno">58</span> <span class="n">download</span><span class="o">.</span><span class="n">download_file</span><span class="p">(</span><span class="s1">'https://linqs-data.soe.ucsc.edu/public/lbc/cora.tgz'</span><span class="p">,</span>
|
|
<span class="lineno">59</span> <span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">'cora.tgz'</span><span class="p">)</span>
|
|
<span class="lineno">60</span> <span class="n">download</span><span class="o">.</span><span class="n">extract_tar</span><span class="p">(</span><span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">'cora.tgz'</span><span class="p">,</span> <span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">())</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<p>Load the dataset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">62</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">include_edges</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
<p>Whether to include edges.
|
|
This is test how much accuracy is lost if we ignore the citation network.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">69</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_edges</span> <span class="o">=</span> <span class="n">include_edges</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
<p>Download dataset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">72</span> <span class="bp">self</span><span class="o">.</span><span class="n">_download</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
<p>Read the paper ids, feature vectors, and labels</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">75</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'Read content file'</span><span class="p">):</span>
|
|
<span class="lineno">76</span> <span class="n">content</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">genfromtxt</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">'cora/cora.content'</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">dtype</span><span class="p">(</span><span class="nb">str</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
<p>Load the citations, it’s a list of pairs of integers.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">78</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'Read citations file'</span><span class="p">):</span>
|
|
<span class="lineno">79</span> <span class="n">citations</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">genfromtxt</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">lab</span><span class="o">.</span><span class="n">get_data_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">'cora/cora.cites'</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>Get the feature vectors</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">features</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">content</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
<p>Normalize the feature vectors</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">84</span> <span class="bp">self</span><span class="o">.</span><span class="n">features</span> <span class="o">=</span> <span class="n">features</span> <span class="o">/</span> <span class="n">features</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">keepdim</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-15'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-15'>#</a>
|
|
</div>
|
|
<p>Get the class names and assign an unique integer to each of them</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">87</span> <span class="bp">self</span><span class="o">.</span><span class="n">classes</span> <span class="o">=</span> <span class="p">{</span><span class="n">s</span><span class="p">:</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">s</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">content</span><span class="p">[:,</span> <span class="o">-</span><span class="mi">1</span><span class="p">]))}</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-16'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-16'>#</a>
|
|
</div>
|
|
<p>Get the labels as those integers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">89</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">classes</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">content</span><span class="p">[:,</span> <span class="o">-</span><span class="mi">1</span><span class="p">]],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">long</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
<p>Get the paper ids</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">92</span> <span class="n">paper_ids</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">content</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<p>Map of paper id to index</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">94</span> <span class="n">ids_to_idx</span> <span class="o">=</span> <span class="p">{</span><span class="n">id_</span><span class="p">:</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">id_</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">paper_ids</span><span class="p">)}</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<p>Empty adjacency matrix - an identity matrix</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">97</span> <span class="bp">self</span><span class="o">.</span><span class="n">adj_mat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">eye</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">bool</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>Mark the citations in the adjacency matrix</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">100</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_edges</span><span class="p">:</span>
|
|
<span class="lineno">101</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">citations</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-21'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-21'>#</a>
|
|
</div>
|
|
<p>The pair of paper indexes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">e1</span><span class="p">,</span> <span class="n">e2</span> <span class="o">=</span> <span class="n">ids_to_idx</span><span class="p">[</span><span class="n">e</span><span class="p">[</span><span class="mi">0</span><span class="p">]],</span> <span class="n">ids_to_idx</span><span class="p">[</span><span class="n">e</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-22'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-22'>#</a>
|
|
</div>
|
|
<p>We build a symmetrical graph, where if paper $i$ referenced
|
|
paper $j$ we place an adge from $i$ to $j$ as well as an edge
|
|
from $j$ to $i$.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">107</span> <span class="bp">self</span><span class="o">.</span><span class="n">adj_mat</span><span class="p">[</span><span class="n">e1</span><span class="p">][</span><span class="n">e2</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="lineno">108</span> <span class="bp">self</span><span class="o">.</span><span class="n">adj_mat</span><span class="p">[</span><span class="n">e2</span><span class="p">][</span><span class="n">e1</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<h2>Graph Attention Network (GAT)</h2>
|
|
<p>This graph attention network has two <a href="index.html">graph attention layers</a>.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">111</span><span class="k">class</span> <span class="nc">GAT</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-24'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-24'>#</a>
|
|
</div>
|
|
<ul>
|
|
<li><code>in_features</code> is the number of features per node</li>
|
|
<li><code>n_hidden</code> is the number of features in the first graph attention layer</li>
|
|
<li><code>n_classes</code> is the number of classes</li>
|
|
<li><code>n_heads</code> is the number of heads in the graph attention layers</li>
|
|
<li><code>dropout</code> is the dropout probability</li>
|
|
</ul>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">118</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_features</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_hidden</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_classes</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_heads</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">dropout</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">126</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-26'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
<p>First graph attention layer where we concatenate the heads</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">129</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer1</span> <span class="o">=</span> <span class="n">GraphAttentionLayer</span><span class="p">(</span><span class="n">in_features</span><span class="p">,</span> <span class="n">n_hidden</span><span class="p">,</span> <span class="n">n_heads</span><span class="p">,</span> <span class="n">is_concat</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="n">dropout</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-27'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-27'>#</a>
|
|
</div>
|
|
<p>Activation function after first graph attention layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">131</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ELU</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
<p>Final graph attention layer where we average the heads</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">133</span> <span class="bp">self</span><span class="o">.</span><span class="n">output</span> <span class="o">=</span> <span class="n">GraphAttentionLayer</span><span class="p">(</span><span class="n">n_hidden</span><span class="p">,</span> <span class="n">n_classes</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">is_concat</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="n">dropout</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-29'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-29'>#</a>
|
|
</div>
|
|
<p>Dropout</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">135</span> <span class="bp">self</span><span class="o">.</span><span class="n">dropout</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="n">dropout</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-30'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-30'>#</a>
|
|
</div>
|
|
<ul>
|
|
<li><code>x</code> is the features vectors of shape <code>[n_nodes, in_features]</code></li>
|
|
<li><code>adj_mat</code> is the adjacency matrix of the form
|
|
<code>[n_nodes, n_nodes, n_heads]</code> or <code>[n_nodes, n_nodes, 1]</code></li>
|
|
</ul>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">137</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">adj_mat</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-31'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-31'>#</a>
|
|
</div>
|
|
<p>Apply dropout to the input</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">144</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dropout</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-32'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-32'>#</a>
|
|
</div>
|
|
<p>First graph attention layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">146</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer1</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">adj_mat</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-33'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-33'>#</a>
|
|
</div>
|
|
<p>Activation function</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">148</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-34'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-34'>#</a>
|
|
</div>
|
|
<p>Dropout</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">150</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dropout</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-35'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-35'>#</a>
|
|
</div>
|
|
<p>Output layer (without activation) for logits</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">152</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">output</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">adj_mat</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-36'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-36'>#</a>
|
|
</div>
|
|
<p>A simple function to calculate the accuracy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">155</span><span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="n">output</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">labels</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-37'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-37'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">159</span> <span class="k">return</span> <span class="n">output</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">eq</span><span class="p">(</span><span class="n">labels</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">labels</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-38'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-38'>#</a>
|
|
</div>
|
|
<h2>Configurations</h2>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">162</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">BaseConfigs</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-39'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-39'>#</a>
|
|
</div>
|
|
<p>Model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">168</span> <span class="n">model</span><span class="p">:</span> <span class="n">GAT</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-40'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-40'>#</a>
|
|
</div>
|
|
<p>Number of nodes to train on</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">170</span> <span class="n">training_samples</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">500</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-41'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-41'>#</a>
|
|
</div>
|
|
<p>Number of features per node in the input</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">172</span> <span class="n">in_features</span><span class="p">:</span> <span class="nb">int</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-42'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-42'>#</a>
|
|
</div>
|
|
<p>Number of features in the first graph attention layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">174</span> <span class="n">n_hidden</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">64</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-43'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-43'>#</a>
|
|
</div>
|
|
<p>Number of heads</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">176</span> <span class="n">n_heads</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-44'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-44'>#</a>
|
|
</div>
|
|
<p>Number of classes for classification</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">178</span> <span class="n">n_classes</span><span class="p">:</span> <span class="nb">int</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-45'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-45'>#</a>
|
|
</div>
|
|
<p>Dropout probability</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">180</span> <span class="n">dropout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.6</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-46'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-46'>#</a>
|
|
</div>
|
|
<p>Whether to include the citation network</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">182</span> <span class="n">include_edges</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-47'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-47'>#</a>
|
|
</div>
|
|
<p>Dataset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">184</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">CoraDataset</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-48'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-48'>#</a>
|
|
</div>
|
|
<p>Number of training iterations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">186</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1_000</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-49'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-49'>#</a>
|
|
</div>
|
|
<p>Loss function</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">188</span> <span class="n">loss_func</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-50'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-50'>#</a>
|
|
</div>
|
|
<p>Device to train on</p>
|
|
<p>This creates configs for device, so that
|
|
we can change the device by passing a config value</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">193</span> <span class="n">device</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">DeviceConfigs</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-51'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-51'>#</a>
|
|
</div>
|
|
<p>Optimizer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">195</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-52'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-52'>#</a>
|
|
</div>
|
|
<p>Initialize</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">197</span> <span class="k">def</span> <span class="nf">initialize</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-53'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-53'>#</a>
|
|
</div>
|
|
<p>Create the dataset</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">202</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataset</span> <span class="o">=</span> <span class="n">CoraDataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">include_edges</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-54'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-54'>#</a>
|
|
</div>
|
|
<p>Get the number of classes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">204</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_classes</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">classes</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-55'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-55'>#</a>
|
|
</div>
|
|
<p>Number of features in the input</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">206</span> <span class="bp">self</span><span class="o">.</span><span class="n">in_features</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">features</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-56'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-56'>#</a>
|
|
</div>
|
|
<p>Create the model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">208</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">GAT</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">in_features</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_hidden</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_classes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_heads</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dropout</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-57'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-57'>#</a>
|
|
</div>
|
|
<p>Move the model to the device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">210</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-58'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-58'>#</a>
|
|
</div>
|
|
<p>Configurable optimizer, so that we can set the configurations
|
|
such as learning rate by passing the dictionary later.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">213</span> <span class="n">optimizer_conf</span> <span class="o">=</span> <span class="n">OptimizerConfigs</span><span class="p">()</span>
|
|
<span class="lineno">214</span> <span class="n">optimizer_conf</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">()</span>
|
|
<span class="lineno">215</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span> <span class="o">=</span> <span class="n">optimizer_conf</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-59'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-59'>#</a>
|
|
</div>
|
|
<h3>Training loop</h3>
|
|
<p>We do full batch training since the dataset is small.
|
|
If we were to sample and train we will have to sample a set of
|
|
nodes for each training step along with the edges that span
|
|
across those selected nodes.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">217</span> <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-60'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-60'>#</a>
|
|
</div>
|
|
<p>Move the feature vectors to the device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">227</span> <span class="n">features</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">features</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-61'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-61'>#</a>
|
|
</div>
|
|
<p>Move the labels to the device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">229</span> <span class="n">labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">labels</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-62'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-62'>#</a>
|
|
</div>
|
|
<p>Move the adjacency matrix to the device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">231</span> <span class="n">edges_adj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">adj_mat</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-63'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-63'>#</a>
|
|
</div>
|
|
<p>Add an empty third dimension for the heads</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">233</span> <span class="n">edges_adj</span> <span class="o">=</span> <span class="n">edges_adj</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-64'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-64'>#</a>
|
|
</div>
|
|
<p>Random indexes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">236</span> <span class="n">idx_rand</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randperm</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">labels</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-65'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-65'>#</a>
|
|
</div>
|
|
<p>Nodes for training</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">238</span> <span class="n">idx_train</span> <span class="o">=</span> <span class="n">idx_rand</span><span class="p">[:</span><span class="bp">self</span><span class="o">.</span><span class="n">training_samples</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-66'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-66'>#</a>
|
|
</div>
|
|
<p>Nodes for validation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">240</span> <span class="n">idx_valid</span> <span class="o">=</span> <span class="n">idx_rand</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">training_samples</span><span class="p">:]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-67'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-67'>#</a>
|
|
</div>
|
|
<p>Training loop</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">243</span> <span class="k">for</span> <span class="n">epoch</span> <span class="ow">in</span> <span class="n">monit</span><span class="o">.</span><span class="n">loop</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">epochs</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-68'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-68'>#</a>
|
|
</div>
|
|
<p>Set the model to training mode</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">245</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">train</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-69'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-69'>#</a>
|
|
</div>
|
|
<p>Make all the gradients zero</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">247</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-70'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-70'>#</a>
|
|
</div>
|
|
<p>Evaluate the model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">249</span> <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">edges_adj</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-71'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-71'>#</a>
|
|
</div>
|
|
<p>Get the loss for training nodes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">251</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">idx_train</span><span class="p">],</span> <span class="n">labels</span><span class="p">[</span><span class="n">idx_train</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-72'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-72'>#</a>
|
|
</div>
|
|
<p>Calculate gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">253</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-73'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-73'>#</a>
|
|
</div>
|
|
<p>Take optimization step</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">255</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-74'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-74'>#</a>
|
|
</div>
|
|
<p>Log the loss</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">257</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'loss.train'</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-75'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-75'>#</a>
|
|
</div>
|
|
<p>Log the accuracy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">259</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'accuracy.train'</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">idx_train</span><span class="p">],</span> <span class="n">labels</span><span class="p">[</span><span class="n">idx_train</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-76'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-76'>#</a>
|
|
</div>
|
|
<p>Set mode to evaluation mode for validation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">262</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-77'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-77'>#</a>
|
|
</div>
|
|
<p>No need to compute gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">265</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-78'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-78'>#</a>
|
|
</div>
|
|
<p>Evaluate the model again</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">267</span> <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">edges_adj</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-79'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-79'>#</a>
|
|
</div>
|
|
<p>Calculate the loss for validation nodes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">269</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">idx_valid</span><span class="p">],</span> <span class="n">labels</span><span class="p">[</span><span class="n">idx_valid</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-80'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-80'>#</a>
|
|
</div>
|
|
<p>Log the loss</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">271</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'loss.valid'</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-81'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-81'>#</a>
|
|
</div>
|
|
<p>Log the accuracy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">273</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'accuracy.valid'</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">(</span><span class="n">output</span><span class="p">[</span><span class="n">idx_valid</span><span class="p">],</span> <span class="n">labels</span><span class="p">[</span><span class="n">idx_valid</span><span class="p">]))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-82'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-82'>#</a>
|
|
</div>
|
|
<p>Save logs</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">276</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-83'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-83'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">279</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-84'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-84'>#</a>
|
|
</div>
|
|
<p>Create configurations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">281</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-85'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-85'>#</a>
|
|
</div>
|
|
<p>Create an experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">283</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'gat'</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-86'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-86'>#</a>
|
|
</div>
|
|
<p>Calculate configurations.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">285</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</span> <span class="p">{</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-87'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-87'>#</a>
|
|
</div>
|
|
<p>Adam optimizer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">287</span> <span class="s1">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Adam'</span><span class="p">,</span>
|
|
<span class="lineno">288</span> <span class="s1">'optimizer.learning_rate'</span><span class="p">:</span> <span class="mf">5e-3</span><span class="p">,</span>
|
|
<span class="lineno">289</span> <span class="s1">'optimizer.weight_decay'</span><span class="p">:</span> <span class="mf">5e-4</span><span class="p">,</span>
|
|
<span class="lineno">290</span> <span class="p">})</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-88'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-88'>#</a>
|
|
</div>
|
|
<p>Initialize</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">292</span> <span class="n">conf</span><span class="o">.</span><span class="n">initialize</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-89'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-89'>#</a>
|
|
</div>
|
|
<p>Start and watch the experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">295</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-90'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-90'>#</a>
|
|
</div>
|
|
<p>Run the training</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">297</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-91'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-91'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">301</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
|
<span class="lineno">302</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
|
</script>
|
|
<!-- MathJax configuration -->
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
tex2jax: {
|
|
inlineMath: [ ['$','$'] ],
|
|
displayMath: [ ['$$','$$'] ],
|
|
processEscapes: true,
|
|
processEnvironments: true
|
|
},
|
|
// Center justify equations in code and markdown cells. Elsewhere
|
|
// we use CSS to left justify single line equations in code cells.
|
|
displayAlign: 'center',
|
|
"HTML-CSS": { fonts: ["TeX"] }
|
|
});
|
|
</script>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
for (var i = 0; i < images.length; ++i) {
|
|
handleImage(images[i])
|
|
}
|
|
}
|
|
|
|
function handleImage(img) {
|
|
img.parentElement.style.textAlign = 'center'
|
|
|
|
var modal = document.createElement('div')
|
|
modal.id = 'modal'
|
|
|
|
var modalContent = document.createElement('div')
|
|
modal.appendChild(modalContent)
|
|
|
|
var modalImage = document.createElement('img')
|
|
modalContent.appendChild(modalImage)
|
|
|
|
var span = document.createElement('span')
|
|
span.classList.add('close')
|
|
span.textContent = 'x'
|
|
modal.appendChild(span)
|
|
|
|
img.onclick = function () {
|
|
console.log('clicked')
|
|
document.body.appendChild(modal)
|
|
modalImage.src = img.src
|
|
}
|
|
|
|
span.onclick = function () {
|
|
document.body.removeChild(modal)
|
|
}
|
|
}
|
|
|
|
handleImages()
|
|
</script>
|
|
</body>
|
|
</html> |