APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding
Summary: APAN enables real-time temporal graph embedding with asynchronous propagation attention, decoupling inference from k-hop querying. This yields millisecond-level inference in dense networks with competitive accuracy; code released. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xuhong Wang (Ant Financial; Shanghai Jiao Tong University)
- 2. Ding Lyu (Shanghai Jiao Tong University)
- 3. Mengjian Li (Ant Financial)
- 4. Yang Xia (Ant Financial)
- 5. Qi Yang (Ant Financial)
- 6. Xinwen Wang (Ant Financial)
- 7. Xinguang Wang (Ant Financial)
- 8. Ping Cui (Shanghai Jiao Tong University)
- 9. Yupu Yang (Shanghai Jiao Tong University)
- 10. Bowen Sun (Ant Financial)
- 11. Zhenyu Guo (Ant Financial)
BibTeX Citation
@inproceedings{wang_sigmod21,
title = {{APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding}},
author = {Wang, Xuhong and Lyu, Ding and Li, Mengjian and Xia, Yang and Yang, Qi and Wang, Xinwen and Wang, Xinguang and Cui, Ping and Yang, Yupu and Sun, Bowen and Guo, Zhenyu},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3457564},
url = {https://dl.acm.org/doi/10.1145/3448016.3457564},
year = {2021}
}
Incoming Citations (Sorted by Pagerank)
Showing 21 of 21 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,922 | When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction | 2025 | VLDB |
| 2 | 11,110 | Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours | 2025 | VLDB |
| 3 | 9,349 | Temporal SIR-GN: Efficient and Effective Structural Representation Learning for Temporal Graphs | 2023 | VLDB |
| 4 | 2,386 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB |
| 5 | 6,109 | GraphAn: Graph-based Subsequence Anomaly Detection | 2020 | VLDB |
| 6 | 8,912 | Historical Embedding-Guided Efficient Large-Scale Federated Graph Learning | 2024 | SIGMOD |
| 7 | 7,011 | GPU-Accelerated Graph Label Propagation for Real-Time Fraud Detection | 2021 | SIGMOD |
| 8 | 4,171 | Accelerating Dynamic Graph Analytics on GPUs | 2018 | VLDB |
| 9 | 4,980 | Decoupled Graph Neural Networks for Large Dynamic Graphs | 2023 | VLDB |
| 10 | 11,154 | NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention | 2024 | SIGMOD |