Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning

TL;DR

This paper introduces InfoMGF, an unsupervised framework for learning fused multiplex graph structures that retain task-relevant information while removing noise, outperforming existing methods including supervised approaches.

Contribution

Proposes a novel unsupervised graph fusion method that refines structure to preserve task-relevant info and eliminate noise, with theoretical guarantees and superior empirical results.

Findings

Outperforms baseline methods on various downstream tasks.

Surpasses some supervised approaches in accuracy.

Demonstrates robustness across different datasets.

Abstract

Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often exhibit a complex nature and contain abundant task-irrelevant noise, severely compromising UMGL's performance. Moreover, existing methods primarily rely on contrastive learning to maximize mutual information across different graphs, limiting them to multiplex graph redundant scenarios and failing to capture view-unique task-relevant information. In this paper, we focus on a more realistic and challenging task: to unsupervisedly learn a fused graph from multiple graphs that preserve sufficient task-relevant information while removing task-irrelevant noise. Specifically, our proposed Information-aware Unsupervised Multiplex Graph Fusion framework (InfoMGF) uses graph structure refinement to eliminate irrelevant noise and simultaneously maximizes view-shared and view-unique task-relevant information, thereby tackling the frontier of non-redundant multiplex graph. Theoretical analyses further guarantee the effectiveness of InfoMGF. Comprehensive experiments against various baselines on different downstream tasks demonstrate its superior performance and robustness. Surprisingly, our unsupervised method even beats the sophisticated supervised approaches. The source code and datasets are available at https://github.com/zxlearningdeep/InfoMGF.