Adaptive Neural Message Passing for Inductive Learning on Hypergraphs

Abstract

Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperMSG, a novel hypergraph learning framework that uses a modular two-level neural message passing strategy to accurately and efficiently propagate information within each hyperedge and across the hyperedges. HyperMSG adapts to the data and task by learning an attention weight associated with each node's degree centrality. Such a mechanism quantifies both local and global importance of a node, capturing the structural properties of a hypergraph. HyperMSG is inductive, allowing inference on previously unseen nodes. Further, it is robust and outperforms state-of-the-art hypergraph learning methods on a wide range of tasks and datasets. Finally, we demonstrate the effectiveness of HyperMSG in learning multimodal relations through detailed experimentation on a challenging multimedia dataset.

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Statistical mechanics of complex networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• Gated Graph Sequence Neural Networks
• DeeperGCN: All You Need to Train Deeper GCNs
• Principal Neighbourhood Aggregation for Graph Nets
• The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
• HNHN: Hypergraph Networks with Hyperedge Neurons
• Visual Analytics for Temporal Hypergraph Model Exploration
• On the Use of ArXiv as a Dataset
• Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs
• UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
• HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
• Stochastic Aggregation in Graph Neural Networks