DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Dongyuan, Tan, Shiyin, Zhang, Ying, Jin, Ming, Pan, Shirui, Okumura, Manabu, Jiang, Renhe
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917152630505472
author Li, Dongyuan
Tan, Shiyin
Zhang, Ying
Jin, Ming
Pan, Shirui
Okumura, Manabu
Jiang, Renhe
author_facet Li, Dongyuan
Tan, Shiyin
Zhang, Ying
Jin, Ming
Pan, Shirui
Okumura, Manabu
Jiang, Renhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06966
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
Li, Dongyuan
Tan, Shiyin
Zhang, Ying
Jin, Ming
Pan, Shirui
Okumura, Manabu
Jiang, Renhe
Machine Learning
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.
title DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
topic Machine Learning
url https://arxiv.org/abs/2408.06966