The growing interest in Temporal Graph Neural Networks (TGNNs) stems from their ability to model complex dynamics and deliver superior performance. However, TGNNs encounter fundamental challenges in capturing long-term dependencies and identifying periodic patterns. To address these limitations, we propose TGFormer, a novel Transformer architecture specifically designed for temporal graphs. Our model redefines temporal graph learning by establishing a trajectory framework that aligns with time series analysis principles. This approach allows TGFormer to derive node representations through systematic analysis of historical interactions, enabling granular examination of node relationships across sequential timestamps. Building upon stochastic process theory, we develop an auto-correlation mechanism that systematically uncovers periodic dependencies in node interactions. This innovation empowers TGFormer to perform dependency discovery and representation aggregation at sub-interaction levels, demonstrating superior efficiency and accuracy compared to conventional attention mechanisms. Experimental validation across six public benchmarks confirms the effectiveness of our approach, with TGFormer at most achieving 9.35\% precision improvement compared to state-of-the-art approaches.
@article{arxiv.2605.24971,
title = {TGFormer: Towards Temporal Graph Transformer with Auto-Correlation Mechanism},
author = {Hongjiang Chen and Pengfei Jiao and Ming Du and Xuan Guo and Zhidong Zhao and Di Jin and Xiao Liu},
journal= {arXiv preprint arXiv:2605.24971},
year = {2026}
}