Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement
Open Access
- 13 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 859-862
Abstract
Inspired by the success of graph contrastive learning, researchers have begun exploring the benefits of contrastive learning over hypergraphs. However, these works have the following limitations in modeling the high-order relationships over unlabeled data: (i) They primarily focus on maximizing the agreements among individual node embeddings while neglecting the capture of group-wise collective behaviors within hypergraphs; (ii) Most of them disregard the importance of the temperature index in discriminating contrastive pairs during contrast optimization. To address these limitations, we propose a novel dual-level Hy perG raph C ontrastive L earning framework with Ad aptive T emperature (HyGCL-AdT ) to boost contrastive learning over hypergraphs. Specifically, unlike most works that merely maximize the agreement of node embeddings in hypergraphs, we propose a dual-level contrast mechanism that not only captures the individual node behaviors in a local context but also models the group-wise collective behaviors of nodes within hyperedges from a community perspective. Besides, we design an adaptive temperature-enhanced contrastive optimization to improve the discrimination ability between contrastive pairs. Empirical experiments conducted on seven benchmark hypergraphs demonstrate that HyGCL-AdT exhibits excellent effectiveness compared to state-of-the-art baseline models. The source code is available at \hrefhttps://github.com/graphprojects/HyGCL-AdT https://github.com/graphprojects/HyGCL-AdT.Keywords
Funding Information
- National Science Foundation (IIS-2321504,IS-2334193,IIS-2203262,IIS-2217239,CNS-2203261,IIS-2340346,CMMI-2146076)
This publication has 10 references indexed in Scilit:
- Malicious Repositories Detection with Adversarial Heterogeneous Graph Contrastive Learning2022
- Rep2Vec: Repository Embedding via Heterogeneous Graph Adversarial Contrastive Learning2022
- Adapting Distilled Knowledge for Few-shot Relation Reasoning over Knowledge Graphs2022
- UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks2021
- Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection2021
- Hypergraph convolution and hypergraph attentionPattern Recognition, 2021
- dStyle-GAN: Generative Adversarial Network based on Writing and Photography Styles for Drug Identification in Darknet Markets2020
- $\alpha$-Satellite: An AI-Driven System and Benchmark Datasets for Dynamic COVID-19 Risk Assessment in the United StatesIEEE Journal of Biomedical and Health Informatics, 2020
- Heterogeneous Graph Neural Network2019
- On Visual Similarity Based 3D Model RetrievalComputer Graphics Forum, 2003