Accurate Learning of Graph Representations with Graph Multiset Pooling

Abstract

Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks. Yet, obtaining an accurate representation for a graph further requires a pooling function that maps a set of node representations into a compact form. A simple sum or average over all node representations considers all node features equally without consideration of their task relevance, and any structural dependencies among them. Recently proposed hierarchical graph pooling methods, on the other hand, may yield the same representation for two different graphs that are distinguished by the Weisfeiler-Lehman test, as they suboptimally preserve information from the node features. To tackle these limitations of existing graph pooling methods, we first formulate the graph pooling problem as a multiset encoding problem with auxiliary information about the graph structure, and propose a Graph Multiset Transformer (GMT) which is a multi-head attention based global pooling layer that captures the interaction between nodes according to their structural dependencies. We show that GMT satisfies both injectiveness and permutation invariance, such that it is at most as powerful as the Weisfeiler-Lehman graph isomorphism test. Moreover, our methods can be easily extended to the previous node clustering approaches for hierarchical graph pooling. Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks with high memory and time efficiency, and obtains even larger performance gain on graph reconstruction and generation tasks.

ICLR 2021

References in corpus (14)

• Prototypical Networks for Few-shot Learning
• Graph Neural Networks: A Review of Methods and Applications
• Representation Learning on Graphs with Jumping Knowledge Networks
• Discriminative Embeddings of Latent Variable Models for Structured Data
• MolGAN: An implicit generative model for small molecular graphs
• TUDataset: A collection of benchmark datasets for learning with graphs
• Benchmarking Graph Neural Networks
• Towards Sparse Hierarchical Graph Classifiers
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Edge Contraction Pooling for Graph Neural Networks
• Position-aware Graph Neural Networks
• Rethinking pooling in graph neural networks
• Retrosynthesis Prediction with Conditional Graph Logic Network
• On the Limitations of Representing Functions on Sets

Cited by in corpus (6)

• Semi-Supervised Hierarchical Graph Classification
• Higher-order Clustering and Pooling for Graph Neural Networks
• Edge Representation Learning with Hypergraphs
• GRAPPA -- A Hybrid Graph Neural Network for Predicting Pure Component Vapor Pressures
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning