Unsupervised multiplex graph representation learning via maximizing coding rate reduction

Wang Xin

doi:10.1016/j.patcog.2025.111557

Unsupervised multiplex graph representation learning via maximizing coding rate reduction

2025-04-25

0

PRE

AI

DOI：10.1016/j.patcog.2025.111557

Original

Original request for help

Save

Abstract

En 中文

Unsupervised multiplex graph representation learning (UMGRL) has gained increasing attention for its effectiveness to extract discriminative and consistent representations without labels. However, previous methods ignore the diversity of extracted representations, leading to sub-optimal results. To address the aforementioned limitations, in this paper, we propose a unified framework to extract discriminative, diverse and consistent representations simultaneously for UMGRL. To do this, we first employ the Multi-Layer Perceptron encoder with the local preserve loss to extract high-quality representations, and then employ two constraints based on the coding rate to constrain representations' diversity, discrimination, and consistency. Comprehensive experiments are conducted to verify the effectiveness of the proposed model. The results show that our method outperforms fourteen existing methods on four public benchmark datasets for three different downstream tasks. The code is available at https://github.com/OllieWangx/D2CMG.

Keywords:

Multiplex graph

Graph representation learning

Unsupervised learning

Coding rate reduction

Unsupervised multiplex graph representation learning via maximizing coding rate reduction

Abstract

Journal

Organization