A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Yang, Ren, Xiaoning
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915357485170688
author Zhou, Yang
Ren, Xiaoning
author_facet Zhou, Yang
Ren, Xiaoning
contents In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences, leading to temporal information loss. This discontinuity not only deteriorates temporal modeling but also hinders optimization by increasing the difficulty of parameter convergence. Our theoretical study quantifies this through a Lipschitz upper bound, showing that large batch sizes enlarge the parameter search space. In response, we propose BADGNN, a novel batch-agnostic framework consisting of two core components: (1) Temporal Lipschitz Regularization (TLR) to control parameter search space expansion, and (2) Adaptive Attention Adjustment (A3) to alleviate attention distortion induced by both regularization and batching. Empirical results on three benchmark datasets show that BADGNN maintains strong performance while enabling significantly larger batch sizes and faster training compared to TGN. Our code is available at Code: https://anonymous.4open.science/r/TGN_Lipichitz-C033/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19282
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams
Zhou, Yang
Ren, Xiaoning
Machine Learning
Graphics
In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences, leading to temporal information loss. This discontinuity not only deteriorates temporal modeling but also hinders optimization by increasing the difficulty of parameter convergence. Our theoretical study quantifies this through a Lipschitz upper bound, showing that large batch sizes enlarge the parameter search space. In response, we propose BADGNN, a novel batch-agnostic framework consisting of two core components: (1) Temporal Lipschitz Regularization (TLR) to control parameter search space expansion, and (2) Adaptive Attention Adjustment (A3) to alleviate attention distortion induced by both regularization and batching. Empirical results on three benchmark datasets show that BADGNN maintains strong performance while enabling significantly larger batch sizes and faster training compared to TGN. Our code is available at Code: https://anonymous.4open.science/r/TGN_Lipichitz-C033/.
title A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams
topic Machine Learning
Graphics
url https://arxiv.org/abs/2506.19282