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
- 2. Guochen Yan
- 3. Yu Shen
- 4. Yang Ling
- 5. Yaoyu Tao
- 6. Bin Cui
- 7. Jian Tang
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 |
|---|---|---|---|---|
| 3,148 | ARM-Net: Adaptive Relation Modeling Network for Structured Data | 2021 | SIGMOD | 7.4751269e-05 |
| 9,098 | Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization | 2023 | SIGMOD | 4.3967784e-05 |
| 11,086 | FedGTA: Topology-aware Averaging for Federated Graph Learning | 2024 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next