GraphAgent: An Effective Knowledge-Guided GNN Model Selection System
Summary: GraphAgent builds a 413K-record Graph-Model Knowledge Graph to guide GNN selection across datasets and tasks. RL meta-feature selection and performance-aware heterogeneous message passing predict and explain top-k models, achieving up to 95.4% nDCG@1. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Mingtao Zhang (Hong Kong Polytechnic University)
- 2. Haoyang Li (Hong Kong Polytechnic University)
- 3. Yuming Xu (Hong Kong Polytechnic University)
- 4. Nicole Hu (Hong Kong Polytechnic University)
- 5. Peng Cheng (Tongji University)
- 6. Chen Jason Zhang (Hong Kong Polytechnic University)
- 7. Qing Li (Hong Kong Polytechnic University)
- 8. Lei Chen (Hong Kong University of Science and Technology)
BibTeX Citation
@article{zhang_vldb26,
title = {{GraphAgent: An Effective Knowledge-Guided GNN Model Selection System}},
author = {Zhang, Mingtao and Li, Haoyang and Xu, Yuming and Hu, Nicole and Cheng, Peng and Zhang, Chen Jason and Li, Qing and Chen, Lei},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4630--4633},
doi = {10.14778/3827998.3828083},
url = {https://doi.org/10.14778/3827998.3828083},
year = {2026}
}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 |
|---|---|---|---|---|
| 4,534 | SimpleTS: An Efficient and Universal Model Selection Framework for Time Series Forecasting | 2023 | VLDB | 6.5561421e-05 |
| 7,640 | KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection | 2025 | SIGMOD | 5.4772833e-05 |
| 7,650 | ModsNet: Performance-aware Top-k Model Search using Exemplar Datasets | 2024 | VLDB | 5.4772833e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,028 | A Scalable AutoML Approach Based on Graph Neural Networks | 2022 | VLDB |
| 2 | 1,772 | ByteGNN: Efficient Graph Neural Network Training at Large Scale | 2022 | VLDB |
| 3 | 6,669 | Efficient Training of Graph Neural Networks on Large Graphs | 2024 | VLDB |
| 4 | 13,617 | Multi-Level Graph Representation Learning Through Predictive Community-based Partitioning | 2025 | SIGMOD |
| 5 | 211 | AliGraph: A Comprehensive Graph Neural Network Platform | 2019 | VLDB |
| 6 | 2,596 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 7 | 6,463 | ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks | 2021 | SIGMOD |
| 8 | 10,520 | A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness | 2026 | SIGMOD |
| 9 | 6,482 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB |
| 10 | 3,899 | Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization | 2021 | VLDB |