Efficiently Harmonizing Information Sharing for Heterogeneous Graph Contrastive Learning

Xiangkai Zhu, Chao Li, Yeyu Yan, Jinhu Fu, Zhongying Zhao, Qingtian Zeng

Abstract: In contrastive learning, the metapath coupled mutual information maximization paradigm struggles to capture rich node context, due to challenge with global representation consistency. Moreover, it simplistically encodes semantic subgraphs in isolation, which not only overlooks potential interactions between different semantic structures but also leads to redundant node encoding. To tackle these challenges, we propose an Efficiently Harmonizing Information Sharing for Heterogeneous Graph Contrastive Learning (HarmoHGCL). Specifically, topology and attribute knowledge are decoupled to capture different relationships and node-specific information. Additionally, a semantic subgraph fusion strategy is proposed to capture the structural interactions between different semantics and employ them as anchor samples. Finally, the above learning modules enable efficient cross-view contrastive learning and harmonize information from different views by node attributes sharing and triple loss strategies. Experimental results show that HarmoHGCL outperforms state-of-the-art methods. The source codes can be accessed at GitHub.1