Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and Topology

Liang Yang, Zhenna Li, Jiaming Zhuo, Jing Liu, Ziyi Ma, Chuan Wang, Zhen Wang, Xiaochun Cao

科研成果: 期刊稿件会议文章同行评审

摘要

As an essential technique for Graph Contrastive Learning (GCL), Graph Augmentation (GA) improves the generalization capability of the GCLs by introducing different forms of the same graph. To ensure information integrity, existing GA strategies have been designed to simultaneously process the two types of information available in graphs: node attributes and graph topology. Nonetheless, these strategies tend to augment the two types of graph information separately, ignoring their correlation, resulting in limited representation ability. To overcome this drawback, this paper proposes a novel GCL framework with a Joint spectrAl augMentation, named GCL-JAM. Motivated the equivalence between the graph learning objective on an attribute graph and the spectral clustering objective on the attribute-interpolated graph, the node attributes are first abstracted as another type of node to harmonize the node attributes and graph topology. The newly constructed graph is then utilized to perform spectral augmentation to capture the correlation during augmentation. Theoretically, the proposed joint spectral augmentation is proved to perturb more inter-class edges and noise attributes compared to separate augmentation methods. Extensive experiments on homophily and heterophily graphs validate the effectiveness and universality of GCL-JAM.

源语言英语
页(从-至)21983-21991
页数9
期刊Proceedings of the AAAI Conference on Artificial Intelligence
39
20
DOI
出版状态已出版 - 11 4月 2025
活动39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025 - Philadelphia, 美国
期限: 25 2月 20254 3月 2025

指纹

探究 'Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and Topology' 的科研主题。它们共同构成独一无二的指纹。

引用此