Unsupervised Multiplex Graph Learning with Complementary and Consistent Information

TL;DR

This paper introduces an unsupervised multiplex graph learning method that effectively addresses out-of-sample and noise issues by using MLP encoders with structure preservation and correlation maximization constraints, outperforming existing methods.

Contribution

It proposes a novel UMGL approach employing MLP encoders with constraints to handle practical issues like out-of-sample and noise, improving effectiveness and efficiency.

Findings

Achieves superior performance over comparison methods.

Effectively handles out-of-sample issue.

Robust against noise in multiplex graph learning.

Abstract

Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks by exploring both complementary information and consistent information among multiple graphs. However, previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. To address the above issues, in this paper, we propose an effective and efficient UMGL method to explore both complementary and consistent information. To do this, our method employs multiple MLP encoders rather than graph convolutional network (GCN) to conduct representation learning with two constraints, i.e., preserving the local graph structure among nodes to handle the out-of-sample issue, and maximizing the correlation of multiple node representations to handle the noise issue. Comprehensive experiments demonstrate that our proposed method achieves superior effectiveness and efficiency over the comparison methods and effectively tackles those two issues. Code is available at https://github.com/LarryUESTC/CoCoMG.