通过因果推理分离多层图中的共性与特异性信息，提升模型可解释性。
Causality-Driven Disentangled Representation Learning in Multiplex Graphs
- 基于因果推断设计自监督框架，解耦共性与私有特征
- 在合成与真实数据集上均优于现有基线方法
- 适合需要可解释图表示的复杂网络分析任务
从多层网络（即节点通过多种关系类型交互的多重图）中学习表征面临挑战，因为共享（公共）信息与层特定（私有）信息相互纠缠，限制了泛化能力和可解释性。本文提出一种基于因果推断的框架——CaDeM，实现自监督下的共性与私有成分解耦。该方法联合执行三步：(i) 对齐各层间的共享嵌入，(ii) 强制私有嵌入捕捉层特定信号，(iii) 应用后门调整，确保共用嵌入仅包含全局信息且与私有表示分离。在合成与真实世界数据集上的实验表明，该方法持续优于现有基线，验证了其在鲁棒且可解释的多重图表示学习中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。