Saved in:
Bibliographic Details
Main Authors: Zhang, Lingling, Qiao, Pengpeng, Zhang, Zhiwei, Yuan, Ye, Wang, Guoren
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915880925921280
author Zhang, Lingling
Qiao, Pengpeng
Zhang, Zhiwei
Yuan, Ye
Wang, Guoren
author_facet Zhang, Lingling
Qiao, Pengpeng
Zhang, Zhiwei
Yuan, Ye
Wang, Guoren
contents Temporal Graph Neural Networks (TGNs) achieve state-of-the-art performance on dynamic graph tasks, yet existing systems focus exclusively on accelerating training -- at inference time, every new edge triggers $O(|V|)$ embedding updates even though only a small fraction of nodes are affected. We present \textbf{StreamTGN}, the first streaming TGN inference system exploiting the inherent locality of temporal graph updates: in an $L$-layer TGN, a new edge affects only nodes within $L$ hops of the endpoints, typically less than 0.2\% on million-node graphs. StreamTGN maintains persistent GPU-resident node memory and uses dirty-flag propagation to identify the affected set $\mathcal{A}$, reducing per-batch complexity from $O(|V|)$ to $O(|\mathcal{A}|)$ with zero accuracy loss. Drift-aware adaptive rebuild scheduling and batched streaming with relaxed ordering further maximize throughput. Experiments on eight temporal graphs (2K--2.6M nodes) show 4.5$\times$--739$\times$ speedup for TGN and up to 4,207$\times$ for TGAT, with identical accuracy. StreamTGN is orthogonal to training optimizations: combining SWIFT with StreamTGN yields 24$\times$ end-to-end speedup across three architectures (TGN, TGAT, DySAT).
format Preprint
id arxiv_https___arxiv_org_abs_2603_21090
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle StreamTGN: A GPU-Efficient Serving System for Streaming Temporal Graph Neural Networks
Zhang, Lingling
Qiao, Pengpeng
Zhang, Zhiwei
Yuan, Ye
Wang, Guoren
Databases
Temporal Graph Neural Networks (TGNs) achieve state-of-the-art performance on dynamic graph tasks, yet existing systems focus exclusively on accelerating training -- at inference time, every new edge triggers $O(|V|)$ embedding updates even though only a small fraction of nodes are affected. We present \textbf{StreamTGN}, the first streaming TGN inference system exploiting the inherent locality of temporal graph updates: in an $L$-layer TGN, a new edge affects only nodes within $L$ hops of the endpoints, typically less than 0.2\% on million-node graphs. StreamTGN maintains persistent GPU-resident node memory and uses dirty-flag propagation to identify the affected set $\mathcal{A}$, reducing per-batch complexity from $O(|V|)$ to $O(|\mathcal{A}|)$ with zero accuracy loss. Drift-aware adaptive rebuild scheduling and batched streaming with relaxed ordering further maximize throughput. Experiments on eight temporal graphs (2K--2.6M nodes) show 4.5$\times$--739$\times$ speedup for TGN and up to 4,207$\times$ for TGAT, with identical accuracy. StreamTGN is orthogonal to training optimizations: combining SWIFT with StreamTGN yields 24$\times$ end-to-end speedup across three architectures (TGN, TGAT, DySAT).
title StreamTGN: A GPU-Efficient Serving System for Streaming Temporal Graph Neural Networks
topic Databases
url https://arxiv.org/abs/2603.21090