Skip to content

A
Annotated Deep Learning Paper Implementations

Greenplum / Annotated Deep Learning Paper Implementations
9 个月 前同步成功

通知 6
Star 0
Fork 0
A
Annotated Deep Learning Paper Implementations

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 ce23bc10 编写于 作者: V Varuna Jayasiri
浏览文件
操作

gat v2 docs

上级 800df5c4
展开全部 隐藏空白更改
内联 并排
Showing with 1953 addition and 4 deletion
docs/graphs/gatv2/experiment.html 0 → 100644
浏览文件 @ ce23bc10
此差异已折叠。
docs/graphs/gatv2/index.html 0 → 100644
浏览文件 @ ce23bc10
此差异已折叠。
docs/graphs/gatv2/readme.html 0 → 100644
浏览文件 @ ce23bc10
<!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=""/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content="Graph Attention Networks v2 (GATv2)"/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/graphs/gatv2/readme.html"/>
<meta property="og:title" content="Graph Attention Networks v2 (GATv2)"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="LabML Neural Networks"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="Graph Attention Networks v2 (GATv2)"/>
<meta property="og:description" content=""/>
<title>Graph Attention Networks v2 (GATv2)</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css">
<link rel="canonical" href="https://nn.labml.ai/graphs/gatv2/readme.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">gatv2</a>
</p>
<p>
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/graphs/gatv2/readme.md">
<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'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1><a href="https://nn.labml.ai/graph/gatv2/index.html">Graph Attention Networks v2 (GATv2)</a></h1>
<p>This is a <a href="https://pytorch.org">PyTorch</a> implementation of the GATv2 opeartor from the paper
<a href="https://arxiv.org/abs/2105.14491">How Attentive are Graph Attention Networks?</a>.</p>
<p>GATv2s work on graph data.
A graph consists of nodes and edges connecting nodes.
For example, in Cora dataset the nodes are research papers and the edges are citations that
connect the papers.</p>
<p>The GATv2 operator which fixes the static attention problem of the standard GAT:
since the linear layers in the standard GAT are applied right after each other, the ranking
of attended nodes is unconditioned on the query node.
In contrast, in GATv2, every node can attend to any other node.</p>
<p>Here is <a href="https://nn.labml.ai/graph/gatv2/experiment.html">the training code</a> for training
a two-layer GAT on Cora dataset.</p>
<p><a href="https://app.labml.ai/run/8e27ad82ed2611ebabb691fb2028a868"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
</div>
<div class='code'>
</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>
\ No newline at end of file
docs/graphs/index.html
浏览文件 @ ce23bc10
...@@ -69,6 +69,7 @@ ...@@ -69,6 +69,7 @@
<h1>Graph Neural Networks</h1> <h1>Graph Neural Networks</h1>
<ul> <ul>
<li><a href="gat/index.html">Graph Attention Networks (GAT)</a></li> <li><a href="gat/index.html">Graph Attention Networks (GAT)</a></li>
<li><a href="gatv2/index.html">Graph Attention Networks v2 (GATv2)</a></li>
</ul> </ul>
</div> </div>
<div class='code'> <div class='code'>
......
docs/index.html
浏览文件 @ ce23bc10
...@@ -115,6 +115,7 @@ implementations.</p> ...@@ -115,6 +115,7 @@ implementations.</p>
<h4>✨ Graph Neural Networks</h4> <h4>✨ Graph Neural Networks</h4>
<ul> <ul>
<li><a href="graphs/gat/index.html">Graph Attention Networks (GAT)</a></li> <li><a href="graphs/gat/index.html">Graph Attention Networks (GAT)</a></li>
<li><a href="gatv2/index.html">Graph Attention Networks v2 (GATv2)</a></li>
</ul> </ul>
<h4>✨ <a href="cfr/index.html">Counterfactual Regret Minimization (CFR)</a></h4> <h4>✨ <a href="cfr/index.html">Counterfactual Regret Minimization (CFR)</a></h4>
<p>Solving games with incomplete information such as poker with CFR.</p> <p>Solving games with incomplete information such as poker with CFR.</p>
......
docs/sitemap.xml
浏览文件 @ ce23bc10
...@@ -281,7 +281,7 @@ ...@@ -281,7 +281,7 @@
<url> <url>
<loc>https://nn.labml.ai/index.html</loc> <loc>https://nn.labml.ai/index.html</loc>
<lastmod>2021-07-17T16:30:00+00:00</lastmod> <lastmod>2021-07-25T16:30:00+00:00</lastmod>
<priority>1.00</priority> <priority>1.00</priority>
</url> </url>
...@@ -741,9 +741,23 @@ ...@@ -741,9 +741,23 @@
</url> </url>
<url>
<loc>https://nn.labml.ai/graphs/gatv2/index.html</loc>
<lastmod>2021-07-25T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>
<url>
<loc>https://nn.labml.ai/graphs/gatv2/experiment.html</loc>
<lastmod>2021-07-25T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>
<url> <url>
<loc>https://nn.labml.ai/graphs/index.html</loc> <loc>https://nn.labml.ai/graphs/index.html</loc>
<lastmod>2021-07-08T16:30:00+00:00</lastmod> <lastmod>2021-07-25T16:30:00+00:00</lastmod>
<priority>1.00</priority> <priority>1.00</priority>
</url> </url>
......
labml_nn/graphs/gatv2/__init__.py
浏览文件 @ ce23bc10
...@@ -117,7 +117,7 @@ class GraphAttentionV2Layer(Module): ...@@ -117,7 +117,7 @@ class GraphAttentionV2Layer(Module):
# We calculate these for each head $k$. *We have omitted $\cdot^k$ for simplicity*. # We calculate these for each head $k$. *We have omitted $\cdot^k$ for simplicity*.
# #
# $$e_{ij} = a(\mathbf{W_l} \overrightarrow{h_i}, \mathbf{W_r} \overrightarrow{h_j}) = # $$e_{ij} = a(\mathbf{W_l} \overrightarrow{h_i}, \mathbf{W_r} \overrightarrow{h_j}) =
# a(\overrightarrow{{g_l}_i}}, \overrightarrow{{g_r}_j}})$$ # a(\overrightarrow{{g_l}_i}, \overrightarrow{{g_r}_j})$$
# #
# $e_{ij}$ is the attention score (importance) from node $j$ to node $i$. # $e_{ij}$ is the attention score (importance) from node $j$ to node $i$.
# We calculate this for each head. # We calculate this for each head.
...@@ -131,7 +131,7 @@ class GraphAttentionV2Layer(Module): ...@@ -131,7 +131,7 @@ class GraphAttentionV2Layer(Module):
# #
# $$e_{ij} = \mathbf{a}^\top \text{LeakyReLU} \Big( # $$e_{ij} = \mathbf{a}^\top \text{LeakyReLU} \Big(
# \Big[ # \Big[
# \overrightarrow{{g_l}_i}} + \overrightarrow{{g_r}_j}} # \overrightarrow{{g_l}_i} + \overrightarrow{{g_r}_j}
# \Big] \Big)$$ # \Big] \Big)$$
# First we calculate # First we calculate
......
readme.md
浏览文件 @ ce23bc10
...@@ -62,6 +62,7 @@ implementations almost weekly. ...@@ -62,6 +62,7 @@ implementations almost weekly.
#### ✨ Graph Neural Networks #### ✨ Graph Neural Networks
* [Graph Attention Networks (GAT)](https://nn.labml.ai/graphs/gat/index.html) * [Graph Attention Networks (GAT)](https://nn.labml.ai/graphs/gat/index.html)
* [Graph Attention Networks v2 (GATv2)](https://nn.labml.ai/graphs/gatv2/index.html)
#### ✨ [Counterfactual Regret Minimization (CFR)](https://nn.labml.ai/cfr/index.html) #### ✨ [Counterfactual Regret Minimization (CFR)](https://nn.labml.ai/cfr/index.html)
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或