Classification of Edge-dependent Labels of Nodes in Hypergraphs

Abstract

A hypergraph is a data structure composed of nodes and hyperedges, where each hyperedge is an any-sized subset of nodes. Due to the flexibility in hyperedge size, hypergraphs represent group interactions (e.g., co-authorship by more than two authors) more naturally and accurately than ordinary graphs. Interestingly, many real-world systems modeled as hypergraphs contain edge-dependent node labels, i.e., node labels that vary depending on hyperedges. For example, on co-authorship datasets, the same author (i.e., a node) can be the primary author in a paper (i.e., a hyperedge) but the corresponding author in another paper (i.e., another hyperedge). In this work, we introduce a classification of edge-dependent node labels as a new problem. This problem can be used as a benchmark task for hypergraph neural networks, which recently have attracted great attention, and also the usefulness of edge-dependent node labels has been verified in various applications. To tackle this problem, we propose WHATsNet, a novel hypergraph neural network that represents the same node differently depending on the hyperedges it participates in by reflecting its varying importance in the hyperedges. To this end, WHATsNet models the relations between nodes within each hyperedge, using their relative centrality as positional encodings. In our experiments, we demonstrate that WHATsNet significantly and consistently outperforms ten competitors on six real-world hypergraphs, and we also show successful applications of WHATsNet to (a) ranking aggregation, (b) node clustering, and (c) product return prediction.

arXiv commentAccepted to KDD 2023

References in corpus (10)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Simplicial Closure and higher-order link prediction
• Hypergraph Motifs: Concepts, Algorithms, and Discoveries
• How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction
• Vector Centrality in Hypergraphs
• Quantum Experiments and Hypergraphs: Multi-Photon Sources for Quantum Interference, Quantum Computation and Quantum Entanglement
• Exploiting Positional Information for Session-based Recommendation
• Classification of Edge-dependent Labels of Nodes in Hypergraphs
• GRPE: Relative Positional Encoding for Graph Transformer
• Core-periphery detection in hypergraphs

Cited by in corpus (6)

• A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
• Classification of Edge-dependent Labels of Nodes in Hypergraphs
• HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction
• Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks
• Graph Neural Networks Based Analog Circuit Link Prediction
• AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks