Self-Attention Graph Pooling

Abstract

Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of generalizing the convolution operation to graphs has been proven to improve performance and is widely used. However, the method of applying downsampling to graphs is still difficult to perform and has room for improvement. In this paper, we propose a graph pooling method based on self-attention. Self-attention using graph convolution allows our pooling method to consider both node features and graph topology. To ensure a fair comparison, the same training procedures and model architectures were used for the existing pooling methods and our method. The experimental results demonstrate that our method achieves superior graph classification performance on the benchmark datasets using a reasonable number of parameters.

10 pages, 3 figures, 4 tables. Accepted to ICML 2019

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Graph Neural Networks: A Review of Methods and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Fast Graph Representation Learning with PyTorch Geometric
• Pitfalls of Graph Neural Network Evaluation
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Towards Sparse Hierarchical Graph Classifiers
• Convolutional Geometric Matrix Completion

Cited by in corpus (50)

• A Gentle Introduction to Deep Learning for Graphs
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Benchmarking Graph Neural Networks
• Causal Attention for Interpretable and Generalizable Graph Classification
• Learning on Attribute-Missing Graphs
• Hierarchical Graph Pooling with Structure Learning
• Understanding Pooling in Graph Neural Networks
• Edge Contraction Pooling for Graph Neural Networks
• GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
• Second-Order Pooling for Graph Neural Networks
• Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• Graph Rationalization with Environment-based Augmentations
• GDPNet: Refining Latent Multi-View Graph for Relation Extraction
• Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
• Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
• GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Graph Pooling via Coarsened Graph Infomax
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
• Semi-Supervised Hierarchical Graph Classification
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
• Higher-order Clustering and Pooling for Graph Neural Networks
• KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Implementing graph neural networks with TensorFlow-Keras
• EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks
• Cell Attention Networks
• Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer
• Sequential Recommendation with Graph Neural Networks
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
• Learning to Count Isomorphisms with Graph Neural Networks
• VulSPG: Vulnerability detection based on slice property graph representation learning
• The Impact of Global Structural Information in Graph Neural Networks Applications
• Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
• Recognizing Predictive Substructures with Subgraph Information Bottleneck
• Ranking Structured Objects with Graph Neural Networks
• Generalizing Downsampling from Regular Data to Graphs
• A Dynamic Reduction Network for Point Clouds
• Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
• Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
• A comprehensive study on the prediction reliability of graph neural networks for virtual screening
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
• Maximal Independent Sets for Pooling in Graph Neural Networks
• Where Did the President Visit Last Week? Detecting Celebrity Trips from News Articles
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features