Causality-Driven Disentangled Representation Learning in Multiplex Graphs

TL;DR

This paper introduces a causal inference-based framework for disentangling shared and private information in multiplex graph representations, improving interpretability and robustness.

Contribution

It proposes a novel self-supervised method that separates common and layer-specific features using causal inference techniques in multiplex graphs.

Findings

Consistent improvements over baseline methods on synthetic datasets.

Enhanced interpretability of multiplex graph representations.

Robustness to different multiplex graph structures.

Abstract

Learning representations from multiplex graphs, i.e., multi-layer networks where nodes interact through multiple relation types, is challenging due to the entanglement of shared (common) and layer-specific (private) information, which limits generalization and interpretability. In this work, we introduce a causal inference-based framework that disentangles common and private components in a self-supervised manner. CaDeM jointly (i) aligns shared embeddings across layers, (ii) enforces private embeddings to capture layer-specific signals, and (iii) applies backdoor adjustment to ensure that the common embeddings capture only global information while being separated from the private representations. Experiments on synthetic and real-world datasets demonstrate consistent improvements over existing baselines, highlighting the effectiveness of our approach for robust and interpretable multiplex graph representation learning.