Causality-Driven Disentangled Representation Learning in Multiplex Graphs
This work addresses the challenge of interpretable and robust representation learning in multiplex graphs, which is incremental as it builds on existing disentanglement methods with a causal approach.
The paper tackled the problem of learning disentangled representations from multiplex graphs by separating shared and layer-specific information, introducing a causal inference-based framework that improved performance on synthetic and real-world datasets.
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.