Timezone: »
Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods are inherently flat and do not learn hierarchical representations of graphs---a limitation that is especially problematic for the task of graph classification, where the goal is to predict the label associated with an entire graph. Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer. Our experimental results show that combining existing GNN methods with DiffPool yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark datasets.
Author Information
Rex Ying (Stanford University)
Jiaxuan You (Stanford University)
2nd CS PhD student in Stanford
Christopher Morris (TU Dortmund University)
Xiang Ren (University of Southern California)
Will Hamilton (McGill University / FAIR)
Jure Leskovec (Stanford University and Pinterest)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Spotlight: Hierarchical Graph Representation Learning with Differentiable Pooling »
Tue Dec 4th 09:55 -- 10:00 PM Room Room 220 E
More from the Same Authors
-
2020 Poster: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Poster: Coresets for Robust Training of Deep Neural Networks against Noisy Labels »
Baharan Mirzasoleiman · Kaidi Cao · Jure Leskovec -
2020 Poster: Graph Information Bottleneck »
Tailin Wu · Hongyu Ren · Pan Li · Jure Leskovec -
2020 Spotlight: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Poster: Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning »
Pan Li · Yanbang Wang · Hongwei Wang · Jure Leskovec -
2020 Poster: Handling Missing Data with Graph Representation Learning »
Jiaxuan You · Xiaobai Ma · Yi Ding · Mykel J Kochenderfer · Jure Leskovec -
2020 Poster: Design Space for Graph Neural Networks »
Jiaxuan You · Zhitao Ying · Jure Leskovec -
2020 Poster: Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs »
Hongyu Ren · Jure Leskovec -
2020 Spotlight: Design Space for Graph Neural Networks »
Jiaxuan You · Zhitao Ying · Jure Leskovec -
2019 Workshop: Graph Representation Learning »
Will Hamilton · Rianne van den Berg · Michael Bronstein · Stefanie Jegelka · Thomas Kipf · Jure Leskovec · Renjie Liao · Yizhou Sun · Petar Veličković -
2019 Poster: Hyperbolic Graph Convolutional Neural Networks »
Ines Chami · Zhitao Ying · Christopher Ré · Jure Leskovec -
2019 Poster: G2SAT: Learning to Generate SAT Formulas »
Jiaxuan You · Haoze Wu · Clark Barrett · Raghuram Ramanujan · Jure Leskovec -
2019 Poster: GNNExplainer: Generating Explanations for Graph Neural Networks »
Zhitao Ying · Dylan Bourgeois · Jiaxuan You · Marinka Zitnik · Jure Leskovec -
2018 Poster: Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation »
Jiaxuan You · Bowen Liu · Zhitao Ying · Vijay Pande · Jure Leskovec -
2018 Poster: Dynamic Network Model from Partial Observations »
Elahe Ghalebi · Baharan Mirzasoleiman · Radu Grosu · Jure Leskovec -
2018 Spotlight: Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation »
Jiaxuan You · Bowen Liu · Zhitao Ying · Vijay Pande · Jure Leskovec -
2018 Spotlight: Dynamic Network Model from Partial Observations »
Elahe Ghalebi · Baharan Mirzasoleiman · Radu Grosu · Jure Leskovec -
2018 Poster: Embedding Logical Queries on Knowledge Graphs »
Will Hamilton · Payal Bajaj · Marinka Zitnik · Dan Jurafsky · Jure Leskovec -
2017 Poster: Inductive Representation Learning on Large Graphs »
Will Hamilton · Zhitao Ying · Jure Leskovec -
2016 Poster: Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making »
Himabindu Lakkaraju · Jure Leskovec -
2013 Workshop: Frontiers of Network Analysis: Methods, Models, and Applications »
Edo M Airoldi · David S Choi · Aaron Clauset · Khalid El-Arini · Jure Leskovec -
2013 Poster: Nonparametric Multi-group Membership Model for Dynamic Networks »
Myunghwan Kim · Jure Leskovec -
2012 Workshop: Social network and social media analysis: Methods, models and applications »
Edo M Airoldi · David S Choi · Khalid El-Arini · Jure Leskovec -
2012 Poster: Learning to Discover Social Circles in Ego Networks »
Julian J McAuley · Jure Leskovec -
2010 Workshop: Networks Across Disciplines: Theory and Applications »
Edo M Airoldi · Anna Goldenberg · Jure Leskovec · Quaid Morris -
2010 Oral: On the Convexity of Latent Social Network Inference »
Seth A Myers · Jure Leskovec -
2010 Poster: On the Convexity of Latent Social Network Inference »
Seth A Myers · Jure Leskovec -
2009 Workshop: Analyzing Networks and Learning With Graphs »
Edo M Airoldi · Jure Leskovec · Jon Kleinberg · Josh Tenenbaum