NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention
Summary: NPA as a plug-in for non-parametric GNNs enabling deep, scalable graph learning. Addresses over-smoothing and feature-agnostic propagation; achieves state-of-the-art on ogbn-papers100M and gains across seven homophilic and five heterophilic graphs. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Wentao Zhang (Peking University)
- 2. Guochen Yan (Peking University)
- 3. Yu Shen (Peking University)
- 4. Yang Ling (Peking University)
- 5. Yaoyu Tao (Tencent)
- 6. Bin Cui (Peking University)
- 7. Jian Tang (HEC Montreal; Mila)
BibTeX Citation
@inproceedings{zhang_sigmod24,
title = {{NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention}},
author = {Zhang, Wentao and Yan, Guochen and Shen, Yu and Ling, Yang and Tao, Yaoyu and Cui, Bin and Tang, Jian},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3626246.3653399},
url = {https://dl.acm.org/doi/10.1145/3626246.3653399},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,390 | ARM-Net: Adaptive Relation Modeling Network for Structured Data | 2021 | SIGMOD | 6.7290926e-05 |
| 9,243 | Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization | 2023 | SIGMOD | 5.2993405e-05 |
| 11,292 | FedGTA: Topology-aware Averaging for Federated Graph Learning | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,048 | AGL: A Scalable System for Industrial-purpose Graph Machine Learning | 2020 | VLDB |
| 2 | 3,896 | Scaling Attributed Network Embedding to Massive Graphs | 2021 | VLDB |
| 3 | 6,630 | Efficient Training of Graph Neural Networks on Large Graphs | 2024 | VLDB |
| 4 | 5,968 | SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization | 2022 | VLDB |
| 5 | 11,110 | Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours | 2025 | VLDB |
| 6 | 223 | AliGraph: A Comprehensive Graph Neural Network Platform | 2019 | VLDB |
| 7 | 2,640 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 8 | 4,980 | Decoupled Graph Neural Networks for Large Dynamic Graphs | 2023 | VLDB |
| 9 | 1,968 | Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank | 2020 | VLDB |
| 10 | 920 | APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding | 2021 | SIGMOD |