You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks

Abstract

Hypergraphs are used to model higher-order interactions amongst agents and there exist many practically relevant instances of hypergraph datasets. To enable efficient processing of hypergraph-structured data, several hypergraph neural network platforms have been proposed for learning hypergraph properties and structure, with a special focus on node classification. However, almost all existing methods use heuristic propagation rules and offer suboptimal performance on many datasets. We propose AllSet, a new hypergraph neural network paradigm that represents a highly general framework for (hyper)graph neural networks and for the first time implements hypergraph neural network layers as compositions of two multiset functions that can be efficiently learned for each task and each dataset. Furthermore, AllSet draws on new connections between hypergraph neural networks and recent advances in deep learning of multiset functions. In particular, the proposed architecture utilizes Deep Sets and Set Transformer architectures that allow for significant modeling flexibility and offer high expressive power. To evaluate the performance of AllSet, we conduct the most extensive experiments to date involving ten known benchmarking datasets and three newly curated datasets that represent significant challenges for hypergraph node classification. The results demonstrate that AllSet has the unique ability to consistently either match or outperform all other hypergraph neural networks across the tested datasets.

arXiv commentICLR 2022

References in corpus (28)

• Prototypical Networks for Few-shot Learning
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Link Prediction in Complex Networks: A Survey
• Higher-order organization of complex networks
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Graph Transformer Networks
• Gated Graph Sequence Neural Networks
• Benchmarking Graph Neural Networks
• PairNorm: Tackling Oversmoothing in GNNs
• Residual Correlation in Graph Neural Network Regression
• The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited
• Accurate Learning of Graph Representations with Graph Multiset Pooling
• Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
• HNHN: Hypergraph Networks with Hyperedge Neurons
• Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
• Contextual Stochastic Block Models
• On the Limitations of Representing Functions on Sets
• New Benchmarks for Learning on Non-Homophilous Graphs
• UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
• HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
• Ubergraphs: A Definition of a Recursive Hypergraph Structure