arXiv (Cornell University) · 2019 · 98 citations · 17 references
ComputingComputer ScienceComputer VisionEdge ComputingMachine LearningDeep LearningGraph AlgorithmsGraph AnalyticsGraph MiningGraph TheoryGraph-based LearningConvolutional Neural NetworksGraph ClassificationGraph Convolutional NetworksGraph Neural NetworksGraph PoolingGraph Representation Learning
Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the notion of edge contraction: EdgePool learns a localized and sparse hard pooling transform. We show that EdgePool outperforms alternative pooling methods, can be easily integrated into most GNN models, and improves performance on both node and graph classification.
17
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
Inductive Representation Learning on Large Graphs
William L. Hamilton, Rex Ying, Jure Leskovec · arXiv (Cornell University) · 2017 · 4.5K citations · Full text