Multi-order hypergraph convolutional networks integrated with self-supervised learning

Hypergraphs, as a powerful representation of information, effectively and naturally depict complex and non-pair-wise relationships in the real world. Hypergraph representation learning is useful for exploring complex relationships implicit in hypergraphs. However, most methods focus on the 1-order n...

Full description

Saved in:
Bibliographic Details
Published in:Complex & intelligent systems 2023-08, Vol.9 (4), p.4389-4401
Main Authors: Huang, Jiahao, Lei, Fangyuan, Jiang, Jianjian, Zeng, Xi, Ma, Ruijun, Dai, Qingyun
Format: Article
Language:English
Subjects:
Ablation
Complexity
Computational Intelligence
Contrastive learning
Data Structures and Information Theory
Engineering
Graph theory
Graphs
Hypergraph
Hypergraph convolutional networks
Multi-order
Mutual information maximization
Neighborhoods
Original Article
Representations
Self-supervised learning
Strategy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hypergraphs, as a powerful representation of information, effectively and naturally depict complex and non-pair-wise relationships in the real world. Hypergraph representation learning is useful for exploring complex relationships implicit in hypergraphs. However, most methods focus on the 1-order neighborhoods and ignore the higher order neighborhood relationships among data on the hypergraph structure. These often result in underutilization of hypergraph structure. In this paper, we exploit the potential of higher order neighborhoods in hypergraphs for representation and propose a Multi-Order Hypergraph Convolutional Network Integrated with Self-supervised Learning. We first encode the multi-channel network of the hypergraph by a high-order spectral convolution operator that captures the multi-order representation of nodes. Then, we introduce an inter-order attention mechanism to preserve the low-order neighborhood information. Finally, to extract valid embedding in the higher order neighborhoods, we incorporate a self-supervised learning strategy based on maximizing mutual information in the multi-order hypergraph convolutional network. Experiments on several hypergraph datasets show that the proposed model is competitive with state-of-the-art baselines, and ablation studies show the effectiveness of higher order neighborhood development, the inter-order attention mechanism, and the self-supervised learning strategy.
ISSN:2199-4536
2198-6053
DOI:10.1007/s40747-022-00964-7