Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization
Summary: Grain reframes GNN data selection as diversified influence maximization, merging propagation with social influence. It introduces a diversified objective and a greedy algorithm with guarantees, boosting learning and core-set efficiency on graphs. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Wentao Zhang (Peking University; Tencent)
- 2. Zhi Yang (Peking University)
- 3. Yexin Wang (Peking University)
- 4. Yu Shen (Peking University)
- 5. Yang Li (Peking University)
- 6. Liang Wang (Peking University)
- 7. Bin Cui (Peking University)
BibTeX Citation
@article{zhang_vldb21,
title = {{Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization}},
author = {Zhang, Wentao and Yang, Zhi and Wang, Yexin and Shen, Yu and Li, Yang and Wang, Liang and Cui, Bin},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {11},
pages = {2473--2482},
doi = {10.14778/3476249.3476295},
url = {https://doi.org/10.14778/3476249.3476295},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,047 | SANCUS: Staleness-Aware Communication-Avoiding Full-Graph Decentralized Training in Large-Scale Graph Neural Networks | 2022 | VLDB | 0.00012313386 |
| 3,027 | Zebra: When Temporal Graph Neural Networks Meet Temporal Personalized PageRank | 2023 | VLDB | 7.7178623e-05 |
| 4,642 | Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning | 2022 | VLDB | 6.4737342e-05 |
| 6,339 | EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs | 2023 | SIGMOD | 5.7918126e-05 |
| 8,628 | Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization | 2023 | SIGMOD | 5.2848769e-05 |
| 8,698 | Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense | 2024 | VLDB | 5.2717835e-05 |
| 8,846 | Fast and Space-Efficient Parallel Algorithms for Influence Maximization | 2024 | VLDB | 5.2498988e-05 |
| 10,145 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD | 5.0597449e-05 |
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 |
|---|---|---|---|---|
| 3,340 | VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition | 2021 | VLDB | 7.3886578e-05 |
| 6,478 | ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks | 2021 | SIGMOD | 5.7547004e-05 |
| 6,693 | Reliable Data Distillation on Graph Convolutional Network | 2020 | SIGMOD | 5.6909845e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,780 | ByteGNN: Efficient Graph Neural Network Training at Large Scale | 2022 | VLDB |
| 2 | 8,649 | D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks | 2024 | VLDB |
| 3 | 2,434 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB |
| 4 | 10,597 | A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness | 2026 | SIGMOD |
| 5 | 6,478 | ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks | 2021 | SIGMOD |
| 6 | 6,339 | EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs | 2023 | SIGMOD |
| 7 | 2,325 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 8 | 4,875 | Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective | 2024 | VLDB |
| 9 | 6,686 | Efficient Training of Graph Neural Networks on Large Graphs | 2024 | VLDB |
| 10 | 11,047 | GraphAgent: An Effective Knowledge-Guided GNN Model Selection System | 2026 | VLDB |