STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
This addresses generalization issues in dynamic graph modeling for domains like traffic or social networks, but it is incremental as it builds on existing STGNN methods with retrieval augmentation.
The paper tackles the problem of Spatio-Temporal Graph Neural Networks (STGNNs) failing to generalize in out-of-distribution scenarios by proposing STRAP, a retrieval-augmented learning framework that enhances generalization; experiments show it consistently outperforms state-of-the-art baselines on real-world streaming graph datasets.
Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework,STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.