# Causality-Driven Disentangled Representation Learning in Multiplex Graphs

arXiv: https://arxiv.org/abs/2603.24105 · HTML: https://mlsanity.com/paper/2603.24105/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [Multilayer Networks](https://mlsanity.com/paper/1309.7233/) (2013)
- [HDMI: High-order Deep Multiplex Infomax](https://mlsanity.com/paper/2102.07810/) (2021)
- [Multi-view Contrastive Graph Clustering](https://mlsanity.com/paper/2110.11842/) (2021)
- [Principled Multilayer Network Embedding](https://mlsanity.com/paper/1709.03551/) (2017)
- [Robust Causal Graph Representation Learning against Confounding Effects](https://mlsanity.com/paper/2208.08584/) (2022)
- [Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation](https://mlsanity.com/paper/2403.11960/) (2024)
- [Unsupervised Multiplex Graph Learning with Complementary and Consistent Information](https://mlsanity.com/paper/2308.01606/) (2023)
- [Representation learning in multiplex graphs: Where and how to fuse information?](https://mlsanity.com/paper/2402.17906/) (2024)
- [Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding](https://mlsanity.com/paper/2312.16834/) (2023)
- [Spectral Clustering Methods for Multiplex Networks](https://mlsanity.com/paper/1703.05355/) (2017)
- [Disentangled Generative Graph Representation Learning](https://mlsanity.com/paper/2408.13471/) (2024)

## Abstract (arXiv)

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.