Out-of-distribution (OOD) generalization issue is a well-known challenge within deep learning tasks. In dynamic graphs, the change of temporal environments is regarded as the main cause of data distribution shift. While numerous OOD studies focusing on environment factors have achieved remarkable performance, they still fail to systematically solve the two issue of environment inference and utilization. In this work, we propose a novel dynamic graph learning model named EpoD based on prompt learning and structural causal model to comprehensively enhance both environment inference and utilization. Inspired by the superior performance of prompt learning in understanding underlying semantic and causal associations, we first design a self-prompted learning mechanism to infer unseen environment factors. We then rethink the role of environment variable within spatio-temporal causal structure model, and introduce a novel causal pathway where dynamic sub-graphs serve as mediating variables. The extracted dynamic subgraph can effectively capture the data distribution shift by incorporating the inferred environment variables into the node-wise dependencies.

Our experiments with multiple real-world dynamic graph datasets demonstrate thatSI-VGRNN andVGRNN consistently outperform the existing baseline and state-of-the-art methods by a significant marginindynamiclinkprediction.

Despite the prevalence ofrecent success inlearning from static graphs, learning from time-evolving graphs remains an open challenge.