Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning

2026-03-02

AI Summary

This work addresses the challenge of out-of-distribution (OOD) shifts in dynamic graphs, where existing methods struggle to simultaneously identify invariant and variant patterns, model the underlying evolution mechanisms, and achieve cross-distribution generalization. To this end, we propose the first end-to-end causal invariant learning framework for dynamic graphs. Our approach explicitly extracts causal structures via a dynamic causal subgraph generator, models the evolution of invariant patterns through a causality-aware spatiotemporal attention mechanism, and incorporates an adaptive environment generator to mitigate distributional shifts. Extensive experiments on multiple real-world and synthetic dynamic graph datasets demonstrate that our method significantly outperforms current state-of-the-art models, achieving robust generalization under complex OOD scenarios.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Although dynamic graph neural networks (DyGNNs) have demonstrated promising capabilities, most existing methods ignore out-of-distribution (OOD) shifts that commonly exist in dynamic graphs. Dynamic graph OOD generalization is non-trivial due to the following challenges: 1) Identifying invariant and variant patterns amid complex graph evolution, 2) Capturing the intrinsic evolution rationale from these patterns, and 3) Ensuring model generalization across diverse OOD shifts despite limited data distribution observations. Although several attempts have been made to tackle these challenges, none has successfully addressed all three simultaneously, and they face various limitations in complex OOD scenarios. To solve these issues, we propose a Dynamic graph Causal Invariant Learning (DyCIL) model for OOD generalization via exploiting invariant spatio-temporal patterns from a causal view. Specifically, we first develop a dynamic causal subgraph generator to identify causal dynamic subgraphs explicitly. Next, we design a causal-aware spatio-temporal attention module to extract the intrinsic evolution rationale behind invariant patterns. Finally, we further introduce an adaptive environment generator to capture the underlying dynamics of distributional shifts. Extensive experiments on both real-world and synthetic dynamic graph datasets demonstrate the superiority of our model over state-of-the-art baselines in handling OOD shifts.

Problem

• out-of-distribution generalization
• dynamic graphs
• causal invariant learning
• graph neural networks
• distributional shifts

Innovation

• causal invariant learning
• dynamic graph neural networks
• out-of-distribution generalization
• spatio-temporal attention
• distributional shift