Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chu, Xu, Xue, Hanlin, Wang, Bingce, Liu, Xiaoyang, Li, Weiping, Mo, Tong, Feng, Tuoyu, Tan, Zhijie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.10010
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912192148799488
author Chu, Xu
Xue, Hanlin
Wang, Bingce
Liu, Xiaoyang
Li, Weiping
Mo, Tong
Feng, Tuoyu
Tan, Zhijie
author_facet Chu, Xu
Xue, Hanlin
Wang, Bingce
Liu, Xiaoyang
Li, Weiping
Mo, Tong
Feng, Tuoyu
Tan, Zhijie
contents Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random noise, overemphasizing recent edges while neglecting earlier ones may lead to the model capturing noise. To address this issue, we propose STAA (SpatioTemporal Activity-Aware Random Walk Diffusion). STAA identifies nodes likely to have noisy edges in spatiotemporal dimensions. Spatially, it analyzes critical topological positions through graph wavelet coefficients. Temporally, it analyzes edge evolution through graph wavelet coefficient change rates. Then, random walks are used to reduce the weights of noisy edges, deriving a diffusion matrix containing spatiotemporal information as an augmented adjacency matrix for dynamic GNN learning. Experiments on multiple datasets show that STAA outperforms other dynamic graph augmentation methods in node classification and link prediction tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10010
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
Chu, Xu
Xue, Hanlin
Wang, Bingce
Liu, Xiaoyang
Li, Weiping
Mo, Tong
Feng, Tuoyu
Tan, Zhijie
Machine Learning
Artificial Intelligence
Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random noise, overemphasizing recent edges while neglecting earlier ones may lead to the model capturing noise. To address this issue, we propose STAA (SpatioTemporal Activity-Aware Random Walk Diffusion). STAA identifies nodes likely to have noisy edges in spatiotemporal dimensions. Spatially, it analyzes critical topological positions through graph wavelet coefficients. Temporally, it analyzes edge evolution through graph wavelet coefficient change rates. Then, random walks are used to reduce the weights of noisy edges, deriving a diffusion matrix containing spatiotemporal information as an augmented adjacency matrix for dynamic GNN learning. Experiments on multiple datasets show that STAA outperforms other dynamic graph augmentation methods in node classification and link prediction tasks.
title Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.10010