DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

TL;DR

DyG-Mamba is a novel dynamic graph model inspired by cognitive theories, which effectively captures long-term dependencies and irregular timespans, leading to state-of-the-art results and improved efficiency.

Contribution

We introduce DyG-Mamba, a dynamic graph model that incorporates forgetting curves and review cycles to enhance long-term dependency modeling and robustness.

Findings

Achieves state-of-the-art performance on most datasets

Demonstrates significant improvements in computational efficiency

Shows enhanced robustness to noisy inputs

Abstract

Dynamic graph modeling aims to uncover evolutionary patterns in real-world systems, enabling accurate social recommendation and early detection of cancer cells. Inspired by the success of recent state space models in efficiently capturing long-term dependencies, we propose DyG-Mamba by translating dynamic graph modeling into a long-term sequence modeling problem. Specifically, inspired by Ebbinghaus' forgetting curve, we treat the irregular timespans between events as control signals, allowing DyG-Mamba to dynamically adjust the forgetting of historical information. This mechanism ensures effective usage of irregular timespans, thereby improving both model effectiveness and inductive capability. In addition, inspired by Ebbinghaus' review cycle, we redefine core parameters to ensure that DyG-Mamba selectively reviews historical information and filters out noisy inputs, further enhancing the model's robustness. Through exhaustive experiments on 12 datasets covering dynamic link prediction and node classification tasks, we show that DyG-Mamba achieves state-of-the-art performance on most datasets, while demonstrating significantly improved computational and memory efficiency. Code is available at https://github.com/Clearloveyuan/DyG-Mamba.