CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Yumeng, Gu, Yu, Li, Tianyi, Qi, Jianzhong, Liu, Zhenghao, Jensen, Christian S., Yu, Ge
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914814407737344
author Song, Yumeng
Gu, Yu
Li, Tianyi
Qi, Jianzhong
Liu, Zhenghao
Jensen, Christian S.
Yu, Ge
author_facet Song, Yumeng
Gu, Yu
Li, Tianyi
Qi, Jianzhong
Liu, Zhenghao
Jensen, Christian S.
Yu, Ge
contents Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data. To such learning, we propose a contrastive hypergraph neural network, CHGNN, that exploits self-supervised contrastive learning techniques to learn from labeled and unlabeled data. First, CHGNN includes an adaptive hypergraph view generator that adopts an auto-augmentation strategy and learns a perturbed probability distribution of minimal sufficient views. Second, CHGNN encompasses an improved hypergraph encoder that considers hyperedge homogeneity to fuse information effectively. Third, CHGNN is equipped with a joint loss function that combines a similarity loss for the view generator, a node classification loss, and a hyperedge homogeneity loss to inject supervision signals. It also includes basic and cross-validation contrastive losses, associated with an enhanced contrastive loss training process. Experimental results on nine real datasets offer insight into the effectiveness of CHGNN, showing that it outperforms 13 competitors in terms of classification accuracy consistently.
format Preprint
id arxiv_https___arxiv_org_abs_2303_06213
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network
Song, Yumeng
Gu, Yu
Li, Tianyi
Qi, Jianzhong
Liu, Zhenghao
Jensen, Christian S.
Yu, Ge
Machine Learning
Artificial Intelligence
Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data. To such learning, we propose a contrastive hypergraph neural network, CHGNN, that exploits self-supervised contrastive learning techniques to learn from labeled and unlabeled data. First, CHGNN includes an adaptive hypergraph view generator that adopts an auto-augmentation strategy and learns a perturbed probability distribution of minimal sufficient views. Second, CHGNN encompasses an improved hypergraph encoder that considers hyperedge homogeneity to fuse information effectively. Third, CHGNN is equipped with a joint loss function that combines a similarity loss for the view generator, a node classification loss, and a hyperedge homogeneity loss to inject supervision signals. It also includes basic and cross-validation contrastive losses, associated with an enhanced contrastive loss training process. Experimental results on nine real datasets offer insight into the effectiveness of CHGNN, showing that it outperforms 13 competitors in terms of classification accuracy consistently.
title CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2303.06213