TIGER: Temporal Interaction Graph Embedding with Restarts
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 478-488
Abstract
Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic node embeddings that vary over time, researchers have proposed a series of temporal graph neural networks for TIGs. However, due to the entangled temporal and structural dependencies, existing methods have to process the sequence of events chronologically and consecutively to ensure node representations are up-to-date. This prevents existing models from parallelization and reduces their flexibility in industrial applications. To tackle the above challenge, in this paper, we propose TIGER, a TIG embedding model that can restart at any timestamp. We introduce a restarter module that generates surrogate representations acting as the warm initialization of node representations. By restarting from multiple timestamps simultaneously, we divide the sequence into multiple chunks and naturally enable the parallelization of the model. Moreover, in contrast to previous models that utilize a single memory unit, we introduce a dual memory module to better exploit neighborhood information and alleviate the staleness problem. Extensive experiments on four public datasets and one industrial dataset are conducted, and the results verify both the effectiveness and the efficiency of our work.Keywords
All Related Versions
Funding Information
- China Postdoctoral Science Foundation (2022M710747)
- National Natural Science Foundation of China (62206059, U1936213)
This publication has 8 references indexed in Scilit:
- CoPE2021
- Self-supervised Representation Learning on Dynamic Graphs2021
- APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding2021
- Learning Temporal Interaction Graph Embedding via Coupled Memory Networks2020
- Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks2019
- Embedding Temporal Network via Neighborhood Formation2018
- Continuous-Time Dynamic Network Embeddings2018
- Learning Node Embeddings in Interaction Graphs2017