SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater.

Dynamic graph learning is crucial for accurately modeling complex systems by integrating topological structure and temporal information within graphs. While memory-based methods are commonly used and excel at capturing short-range temporal correlations, they struggle with modeling long-range dependencies, harmonizing long-range and short-range correlations, and integrating structural information effectively. To address these challenges, we present SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater. SALoM features a memory module that addresses gradient vanishing and information forgetting, enabling the capture of long-term dependencies across various time scales. Additionally, SALoM utilizes a long-short memory updater (LSMU) to dynamically balance long-range and short-range temporal correlations, preventing over-generalization. By integrating co-occurrence encoding and LSMU through information bottleneck-based fusion, SALoM effectively captures both the structural and temporal information within graphs. Experimental results across various graph datasets demonstrate SALoM’s superior performance, achieving state-of-the-art results in dynamic graph link prediction.

Recommended citation: Hanwen Liu, Longjiao Zhang, Rui Wang, Tongya Zheng, Sai Wu, Chang Yao, Mingli Song, "SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater." the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego Convention Center, Nov 30th to Dec 7th, 2025