不依赖环境标注，通过分布稳定性识别因果子图提升图模型泛化能力
Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
- 基于分布稳定性准则，量化区分因果与非因果子图
- 在两个基准数据集上超越现有最优方法，泛化性能显著提升
- 适合追求无监督因果建模与鲁棒图学习的研究者
在分布变化下的泛化能力仍是图神经网络面临的重大挑战。现有方法多依赖需大量标注的不变风险最小化（IRM）框架，或依赖启发式生成的合成划分。本文提出一种无需IRM的因果子图识别方法：首先发现因果子图在不同环境间分布变异远小于非因果部分，提出并理论证明了不变分布准则；进一步系统揭示分布偏移与表征范数间的定量关系，深入解析其机制；最终设计一种基于范数引导的不变分布目标，实现因果子图发现与预测。在两个主流基准上的大量实验表明，该方法在图泛化任务中持续优于当前最优方法。
原文摘要 · Abstract (English)
Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimization (IRM) framework, requiring costly environment annotations or heuristically generated synthetic splits. To circumvent these limitations, in this work, we aim to develop an IRM-free method for capturing causal subgraphs. We first identify that causal subgraphs exhibit substantially smaller distributional variations than non-causal components across diverse environments, which we formalize as the Invariant Distribution Criterion and theoretically prove in this paper. Building on this criterion, we systematically uncover the quantitative relationship between distributional shift and representation norm for identifying the causal subgraph, and investigate its underlying mechanisms in depth. Finally, we propose an IRM-free method by introducing a norm-guided invariant distribution objective for causal subgraph discovery and prediction. Extensive experiments on two widely used benchmarks demonstrate that our method consistently outperforms state-of-the-art methods in graph generalization.
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。