On Data-Aware Global Explainability of Graph Neural Networks
Summary: DAG-Explainer targets data-aware global explanations for pretrained GNNs, jointly optimizing model faithfulness, distribution compliance, and class discrimination. It formalizes the NP-hard selection problem and provides a randomized greedy algorithm with improved approximation guarantees. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
BibTeX Citation
@article{lv_vldb23,
title = {{On Data-Aware Global Explainability of Graph Neural Networks}},
author = {Lv, Ge and Chen, Lei},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {11},
pages = {3447--3460},
doi = {10.14778/3611479.3611538},
url = {https://doi.org/10.14778/3611479.3611538},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,732 | Explaining GNN-based Recommendations in Logic | 2025 | VLDB | 5.1349531e-05 |
| 10,523 | Differentially Private Explanations for Clusters | 2026 | SIGMOD | 4.9793485e-05 |
| 10,706 | Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling | 2026 | VLDB | 4.9793485e-05 |
| 10,739 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 578 | The Complexity of Causality and Responsibility for Query Answers and non-Answers | 2011 | VLDB | 0.00016096504 |
| 1,941 | Interpretable Data-Based Explanations for Fairness Debugging | 2022 | SIGMOD | 9.3297671e-05 |
| 2,222 | Explaining Query Answers with Explanation-Ready Databases | 2016 | VLDB | 8.8109051e-05 |
| 6,699 | Toward Interpretable and Actionable Data Analysis with Explanations and Causality | 2022 | VLDB | 5.7058728e-05 |
| 7,703 | Interactive Query Explanations Using Fine Grained Provenance | 2022 | SIGMOD | 5.4744994e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,669 | Efficient Training of Graph Neural Networks on Large Graphs | 2024 | VLDB |
| 2 | 10,977 | GraphAgent: An Effective Knowledge-Guided GNN Model Selection System | 2026 | VLDB |
| 3 | 10,739 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 4 | 4,898 | Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective | 2024 | VLDB |
| 5 | 5,051 | Decoupled Graph Neural Networks for Large Dynamic Graphs | 2023 | VLDB |
| 6 | 11,763 | HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks | 2023 | VLDB |
| 7 | 6,324 | EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs | 2023 | SIGMOD |
| 8 | 4,825 | DAHA: Accelerating GNN Training with Data and Hardware Aware Execution Planning | 2024 | VLDB |
| 9 | 13,582 | Scalable GNN Explanations with Distributed Shapley Values | 2026 | VLDB |
| 10 | 10,105 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD |