TGOnline: Enhancing Temporal Graph Learning with Adaptive Online Meta-Learning

Ruijie Wang, Jingyuan Huang, Yutong Zhang, Jinyang Li, Yufeng Wang, Wanyu Zhao, Shengzhong Liu, Thirimadura Charith Yasendra Mendis, Tarek Abdelzaher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Temporal graphs, depicting time-evolving node connections through temporal edges, are extensively utilized in domains where temporal connection patterns are essential, such as recommender systems, financial networks, healthcare, and sensor networks. Despite recent advancements in temporal graph representation learning, performance degradation occurs with periodic collections of new temporal edges, owing to their dynamic nature and newly emerging information. This paper investigates online representation learning on temporal graphs, aiming for efficient updates of temporal models to sustain predictive performance during deployment. Unlike costly retraining or exclusive fine-tuning susceptible to catastrophic forgetting, our approach aims to distill information from previous model parameters and adapt it to newly gathered data. To this end, we propose TGOnline, an adaptive online meta-learning framework, tackling two key challenges. First, to distill valuable knowledge from complex temporal parameters, we establish an optimization objective that determines new parameters, either by leveraging global ones or by placing greater reliance on new data, where global parameters are meta-trained across various data collection periods to enhance temporal generalization. Second, to accelerate the online distillation process, we introduce an edge reduction mechanism that skips new edges lacking additional information and a node deduplication mechanism to prevent redundant computation within training batches on new data. Extensive experiments on four real-world temporal graphs demonstrate the effectiveness and efficiency of TGOnline for online representation learning, outperforming 18 state-of-the-art baselines. Notably, TGOnline not only outperforms the commonly utilized retraining strategy but also achieves a significant speedup of ∼30x.

Original languageEnglish (US)
Title of host publicationSIGIR 2024 - Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval
PublisherAssociation for Computing Machinery
Pages1659-1669
Number of pages11
ISBN (Electronic)9798400704314
DOIs
StatePublished - Jul 10 2024
Event47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024 - Washington, United States
Duration: Jul 14 2024Jul 18 2024

Publication series

NameSIGIR 2024 - Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024
Country/TerritoryUnited States
CityWashington
Period7/14/247/18/24

Keywords

  • efficient online learning
  • meta-learning
  • temporal graph learning

ASJC Scopus subject areas

  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'TGOnline: Enhancing Temporal Graph Learning with Adaptive Online Meta-Learning'. Together they form a unique fingerprint.

Cite this