Yongxiang Liao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yongxiang Liao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Xuehao Zheng
Tencent Weixin Group, Shenzhen, China
1 shared publication - Yangyong Zhu
College of Computer Science and Artificial Intelligence, Fudan Unviersity, Shanghai, China and Shanghai Data Research Institute, Shanghai, China
1 shared publication - Yao Zhang
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China
1 shared publication - Yiheng Sun
Tencent Weixin Group, Shenzhen, China
1 shared publication - Yucheng Jin
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University Shanghai, Fudan University, Shanghai, China
1 shared publication - Yun Xiong
Fudan University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 478-488
TIGER: Temporal Interaction Graph Embedding with Restarts
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.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 478-488
Open AccessTIGER: Temporal Interaction Graph Embedding with Restarts
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.