Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

TL;DR

This paper introduces EAGLE, a novel environment-aware framework for dynamic graph neural networks that enhances out-of-distribution generalization by modeling complex environments and discovering invariant spatio-temporal patterns.

Contribution

The paper proposes a new environment-aware dynamic graph learning method that models coupled environments and exploits invariant patterns for better OOD generalization.

Findings

EAGLE outperforms state-of-the-art methods on real-world datasets.

The approach effectively models complex environments on dynamic graphs.

Invariant pattern recognition improves prediction robustness under distribution shifts.

Abstract

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatio-temporal invariant patterns. Specifically, we first design the environment-aware EA-DGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.