Abstract
Although unsupervised multiplex graph representation learning (UMGRL) has been a hot research topic, existing UMGRL methods still has limitations to be addressed. For example, previous works either preserve structural information by ignoring the impact of heterophily in the graph structure or only focus on node-level consistency by ignoring class-level consistency. To address these issues, in this paper, we propose a new UMGRL method, CH-MGRL (Consistency and Homophily-Aware Multiplex Graph Representation Learning), to explore both homophily and consistency in the multiplex graph. Specifically, we propose to restructure the multi-order relationships of every graph between every node and its multi-order neighbors to improve the homophily and reduce the impact of the heterophily in the graph structure. We also design a contrastive loss based on a self-expression matrix of the node representation to achieve node-level and class-level consistency. Furthermore, we theoretically prove our method to achieve class-level consistency. Extensive experimental results on real datasets verify the effectiveness of the proposed method with respect to node classification tasks, compared to SOTA methods.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
"Consistent and Homophily-Aware Representation Learning for Multiplex Graphs", Technical Disclosure Commons, (May 04, 2025)
https://www.tdcommons.org/dpubs_series/8082