update for final release

data/bibliography.bib

@@ -1733,3 +1733,12 @@ @ARTICLE{Pattanaik2020-jj
   primaryClass  = "q-bio.QM",
   eprint        = "2012.00094"
 }
+
+@article{daigavane2021understanding,
+  author = {Daigavane, Ameya and Ravindran, Balaraman and Aggarwal, Gaurav},
+  title = {Understanding Convolutions on Graphs},
+  journal = {Distill},
+  year = {2021},
+  note = {https://distill.pub/2021/understanding-gnns},
+  doi = {10.23915/distill.00032}
+}

index.html

@@ -102,17 +102,17 @@ <h3>Affiliations</h3>
 <p class="affiliation"><span class="affiliation">Google Research</span></p>
 
 </div>
-<div><h3>Published</h3><p>January 5, 2021</p></div>
+<div><h3>Published</h3><p>August 17, 2021</p></div>
 <div>
   <h3>DOI</h3>
-  <p><a href="https://doi.org/10.23915/distill.00026">10.55555/distill.00026</a></p>
+  <p><a href="https://doi.org/10.23915/distill.00033">10.23915/distill.00033</a></p>
 </div>
 </div>
 </d-byline>
 
 <d-article>
 
-<p><em>This article is one of two Distill publications about graph neural networks. Take a look at <a href="https://drafts.distill.pub/distillpub/exploring-graph-nns/">Understanding Convolutions on Graphs</a> to understand how convolutions over images generalize naturally to convolutions over graphs.</em></p>
+<p><em>This article is one of two Distill publications about graph neural networks. Take a look at <a href="https://staging.distill.pub/2021/understanding-gnns/">Understanding Convolutions on Graphs</a><d-cite key="daigavane2021understanding"></d-cite> to understand how convolutions over images generalize naturally to convolutions over graphs.</em></p>
 <p>Graphs are all around us; real world objects are often defined in terms of their connections to other things. A set of objects, and the connections between them, are naturally expressed as a <em>graph</em>. Researchers have developed neural networks that operate on graph data (called graph neural networks, or GNNs) for over a decade<d-cite key='Scarselli2009-ku'></d-cite>. Recent developments have increased their capabilities and expressive power. We are starting to see practical applications in areas such as antibacterial discovery <d-cite key="Stokes2020-az"></d-cite>, physics simulations  <d-cite key="Sanchez-Gonzalez2020-yo"></d-cite>, fake news detection <d-cite key="Monti2019-tf"></d-cite>, traffic prediction <d-cite key="undated-sy"></d-cite> and recommendation systems <d-cite key="Eksombatchai2017-il"></d-cite>.</p>
 <p>This article explores and explains modern graph neural networks. We divide this work into four parts. First, we look at what kind of data is most naturally phrased as a graph, and some common examples. Second, we explore what makes graphs different from other types of data, and some of the specialized choices we have to make when using graphs. Third, we build a modern GNN, walking through each of the parts of the model, starting with historic modeling innovations in the field. We move gradually from a bare-bones implementation to a state-of-the-art GNN model. Fourth and finally, we provide a GNN playground where you can play around with a real-word task and dataset to build a stronger intuition of how each component of a GNN model contributes to the predictions it makes.</p>
 <p>To start, let’s establish what a graph is. A graph represents the relations (<em>edges</em>) between a collection of entities (<em>nodes</em>). </p>

public/bibliography.bib

@@ -1733,3 +1733,12 @@ @ARTICLE{Pattanaik2020-jj
   primaryClass  = "q-bio.QM",
   eprint        = "2012.00094"
 }
+
+@article{daigavane2021understanding,
+  author = {Daigavane, Ameya and Ravindran, Balaraman and Aggarwal, Gaurav},
+  title = {Understanding Convolutions on Graphs},
+  journal = {Distill},
+  year = {2021},
+  note = {https://distill.pub/2021/understanding-gnns},
+  doi = {10.23915/distill.00032}
+}

public/index.html

@@ -34,42 +34,45 @@
 <link rel="stylesheet" href="graph-description.c0d85959.css">
 <link rel="stylesheet" href="graph-description-embeddings.95e72025.css">
 
+
 <d-front-matter>
   <script type="text/json">
     {
-      "title": "A Gentle Introduction to Graph Neural Networks",
-      "description": "What components are needed for building learning algorithms that leverage the structure and properties of graphs?",
-      "authors": [{
-        "author": "Benjamin Sanchez-Lengeling",
-        "affiliations": [{
-          "name": "Google Research",
-          "affiliationURL": "https://research.google/teams/brain/"
-        }]
-      }, {
-        "author": "Emily Reif",
-        "affiliations": [{
-          "name": "Google Research",
-          "affiliationURL": "https://research.google/teams/brain/"
-        }]
-      }, {
-        "author": "Adam Pearce",
-        "authorURL": "https://roadtolarissa.com",
-        "affiliations": [{
-          "name": "Google Research",
-          "affiliationURL": "https://research.google/teams/brain/"
-        }]
-      }, {
-        "author": "Alex Wiltschko",
-        "affiliations": [{
-          "name": "Google Research",
-          "affiliationURL": "https://research.google/teams/brain/"
-        }]
+    "title": "A Gentle Introduction to Graph Neural Networks",
+    "description": "What components are needed for building learning algorithms that leverage the structure and properties of graphs?",
+    "authors": [{
+      "author": "Benjamin Sanchez-Lengeling",
+      "affiliations": [{
+        "name": "Google Research",
+        "affiliationURL": "https://research.google/teams/brain/"
+      }]
+    }, {
+      "author": "Emily Reif",
+      "affiliations": [{
+        "name": "Google Research",
+        "affiliationURL": "https://research.google/teams/brain/"
+      }]
+    }, {
+      "author": "Adam Pearce",
+      "authorURL": "https://roadtolarissa.com",
+      "affiliations": [{
+        "name": "Google Research",
+        "affiliationURL": "https://research.google/teams/brain/"
       }]
+    }, {
+      "author": "Alex Wiltschko",
+      "affiliations": [{
+        "name": "Google Research",
+        "affiliationURL": "https://research.google/teams/brain/"
+      }]
+    }]
     }
   </script>
 </d-front-matter>
 
 
+
+
 <d-title>
   <h1>A Gentle Introduction to Graph Neural Networks</h1>
   <p>Neural networks have been adapted to leverage the structure and properties of graphs. We explore the components needed for building a graph neural network - and motivate the design choices behind them.</p>
@@ -99,17 +102,17 @@ <h3>Affiliations</h3>
 <p class="affiliation"><span class="affiliation">Google Research</span></p>
 
 </div>
-<div><h3>Published</h3><p>January 5, 2021</p></div>
+<div><h3>Published</h3><p>August 17, 2021</p></div>
 <div>
   <h3>DOI</h3>
-  <p><a href="https://doi.org/10.23915/distill.00026">10.55555/distill.00026</a></p>
+  <p><a href="https://doi.org/10.23915/distill.00033">10.23915/distill.00033</a></p>
 </div>
 </div>
 </d-byline>
 
 <d-article>
 
-<p><em>This article is one of two Distill publications about graph neural networks. Take a look at <a href="https://drafts.distill.pub/distillpub/exploring-graph-nns/">Understanding Convolutions on Graphs</a> to understand how convolutions over images generalize naturally to convolutions over graphs.</em></p>
+<p><em>This article is one of two Distill publications about graph neural networks. Take a look at <a href="https://staging.distill.pub/2021/understanding-gnns/">Understanding Convolutions on Graphs</a><d-cite key="daigavane2021understanding"></d-cite> to understand how convolutions over images generalize naturally to convolutions over graphs.</em></p>
 <p>Graphs are all around us; real world objects are often defined in terms of their connections to other things. A set of objects, and the connections between them, are naturally expressed as a <em>graph</em>. Researchers have developed neural networks that operate on graph data (called graph neural networks, or GNNs) for over a decade<d-cite key="Scarselli2009-ku"></d-cite>. Recent developments have increased their capabilities and expressive power. We are starting to see practical applications in areas such as antibacterial discovery <d-cite key="Stokes2020-az"></d-cite>, physics simulations  <d-cite key="Sanchez-Gonzalez2020-yo"></d-cite>, fake news detection <d-cite key="Monti2019-tf"></d-cite>, traffic prediction <d-cite key="undated-sy"></d-cite> and recommendation systems <d-cite key="Eksombatchai2017-il"></d-cite>.</p>
 <p>This article explores and explains modern graph neural networks. We divide this work into four parts. First, we look at what kind of data is most naturally phrased as a graph, and some common examples. Second, we explore what makes graphs different from other types of data, and some of the specialized choices we have to make when using graphs. Third, we build a modern GNN, walking through each of the parts of the model, starting with historic modeling innovations in the field. We move gradually from a bare-bones implementation to a state-of-the-art GNN model. Fourth and finally, we provide a GNN playground where you can play around with a real-word task and dataset to build a stronger intuition of how each component of a GNN model contributes to the predictions it makes.</p>
 <p>To start, let’s establish what a graph is. A graph represents the relations (<em>edges</em>) between a collection of entities (<em>nodes</em>). </p>