Community-Invariant Graph Contrastive Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tan, Shiyin, Li, Dongyuan, Jiang, Renhe, Zhang, Ying, Okumura, Manabu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914781277978624
author Tan, Shiyin
Li, Dongyuan
Jiang, Renhe
Zhang, Ying
Okumura, Manabu
author_facet Tan, Shiyin
Li, Dongyuan
Jiang, Renhe
Zhang, Ying
Okumura, Manabu
contents Graph augmentation has received great attention in recent years for graph contrastive learning (GCL) to learn well-generalized node/graph representations. However, mainstream GCL methods often favor randomly disrupting graphs for augmentation, which shows limited generalization and inevitably leads to the corruption of high-level graph information, i.e., the graph community. Moreover, current knowledge-based graph augmentation methods can only focus on either topology or node features, causing the model to lack robustness against various types of noise. To address these limitations, this research investigated the role of the graph community in graph augmentation and figured out its crucial advantage for learnable graph augmentation. Based on our observations, we propose a community-invariant GCL framework to maintain graph community structure during learnable graph augmentation. By maximizing the spectral changes, this framework unifies the constraints of both topology and feature augmentation, enhancing the model's robustness. Empirical evidence on 21 benchmark datasets demonstrates the exclusive merits of our framework. Code is released on Github (https://github.com/ShiyinTan/CI-GCL.git).
format Preprint
id arxiv_https___arxiv_org_abs_2405_01350
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Community-Invariant Graph Contrastive Learning
Tan, Shiyin
Li, Dongyuan
Jiang, Renhe
Zhang, Ying
Okumura, Manabu
Machine Learning
Social and Information Networks
Graph augmentation has received great attention in recent years for graph contrastive learning (GCL) to learn well-generalized node/graph representations. However, mainstream GCL methods often favor randomly disrupting graphs for augmentation, which shows limited generalization and inevitably leads to the corruption of high-level graph information, i.e., the graph community. Moreover, current knowledge-based graph augmentation methods can only focus on either topology or node features, causing the model to lack robustness against various types of noise. To address these limitations, this research investigated the role of the graph community in graph augmentation and figured out its crucial advantage for learnable graph augmentation. Based on our observations, we propose a community-invariant GCL framework to maintain graph community structure during learnable graph augmentation. By maximizing the spectral changes, this framework unifies the constraints of both topology and feature augmentation, enhancing the model's robustness. Empirical evidence on 21 benchmark datasets demonstrates the exclusive merits of our framework. Code is released on Github (https://github.com/ShiyinTan/CI-GCL.git).
title Community-Invariant Graph Contrastive Learning
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2405.01350