APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding
Authors:
Top Cited Papers
Open Access
- 9 June 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2628-2638
Abstract
To capture higher-order structural features, most GNN-based algorithms learn node representations incorporating k-hop neighbors' information. Due to the high time complexity of querying k-hop neighbors, most graph algorithms cannot be deployed in a giant dense temporal network to execute millisecond-level inference. This problem dramatically limits the potential of applying graph algorithms in certain areas, especially financial fraud detection. Therefore, we propose Asynchronous Propagation Attention Network, an asynchronous continuous time dynamic graph algorithm for real-time temporal graph embedding. Traditional graph models usually execute two serial operations: first graph querying and then model inference. Different from previous graph algorithms, we decouple model inference and graph computation to alleviate the damage of the heavy graph query operation to the speed of model inference. Extensive experiments demonstrate that the proposed method can achieve competitive performance while greatly improving the inference speed. The source code is published at a Github repository.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (51777122)
This publication has 13 references indexed in Scilit:
- NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization2019
- Embedding Temporal Network via Neighborhood Formation2018
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
- A Comprehensive Survey of Graph Embedding: Problems, Techniques, and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2018
- Network Embedding as Matrix Factorization2018
- Sequential Recommendation with User Memory Networks2018
- Continuous-Time Dynamic Network Embeddings2018
- Structural Deep Network Embedding2016
- node2vec2016
- DeepWalk2014