Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization
Summary: Scapin reframes perturbation for GNNs as influence-maximization, enabling scalable edge edits. Proposes edge-influence model with decomposed, submodular objectives and a submodularity-based edge addition algorithm, yielding runtime/memory efficiency. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yexin Wang (Peking University)
- 2. Zhi Yang (Peking University)
- 3. Junqi Liu (Peking University)
- 4. Wentao Zhang (Peking University)
- 5. Bin Cui (Peking University)
BibTeX Citation
@inproceedings{wang_sigmod23,
title = {{Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization}},
author = {Wang, Yexin and Yang, Zhi and Liu, Junqi and Zhang, Wentao and Cui, Bin},
series = {{SIGMOD} '23},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3589291},
url = {https://dl.acm.org/doi/10.1145/3589291},
year = {2023}
}
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,076 | Efficient Approximation Algorithms for Minimum Cost Seed Selection with Probabilistic Coverage Guarantee | 2024 | SIGMOD | 5.2283159e-05 |
| 10,871 | Efficient GPU-Accelerated Adaptive Minimum Cost Seed Selection | 2026 | VLDB | 4.9793485e-05 |
| 11,501 | NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention | 2024 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,482 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB |
| 2 | 13,585 | Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy | 2026 | VLDB |
| 3 | 8,358 | Demystifying Graph Sparsification Algorithms in Graph Properties Preservation | 2024 | VLDB |
| 4 | 2,596 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 5 | 8,127 | Coarsening Massive Influence Networks for Scalable Diffusion Analysis | 2017 | SIGMOD |
| 6 | 9,963 | Fast and Space-Efficient Parallel Algorithms for Influence Maximization | 2024 | VLDB |
| 7 | 11,501 | NPA: Improving Large-scale Graph Neural Networks with Non-parametric Attention | 2024 | SIGMOD |
| 8 | 9,370 | Topology-preserving Graph Coarsening: An Elementary Collapse-based Approach | 2024 | VLDB |
| 9 | 5,124 | SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization | 2022 | VLDB |
| 10 | 13,582 | Scalable GNN Explanations with Distributed Shapley Values | 2026 | VLDB |