On the Feasibility of Fidelity^- for Graph Pruning
Not on the map. Why?
Abstract (arXiv)
As one of popular quantitative metrics to assess the quality of explanation of graph neural networks (GNNs), fidelity measures the output difference after removing unimportant parts of the input graph. Fidelity has been widely used due to its straightforward interpretation that the underlying model should produce similar predictions when features deemed unimportant from the explanation are removed. This raises a natural question: "Does fidelity induce a global (soft) mask for graph pruning?" To solve this, we aim to explore the potential of the fidelity measure to be used for graph pruning, eventually enhancing the GNN models for better efficiency. To this end, we propose Fidelity^--inspired Pruning (FiP), an effective framework to construct global edge masks from local explanations. Our empirical observations using 7 edge attribution methods demonstrate that, surprisingly, general eXplainable AI methods outperform methods tailored to GNNs in terms of graph pruning performance.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 17 Jun 2024.
Builds on
23 of 29 references.
References · 23
- 2017Graph Attention Networkscited by 8,923
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
11 more
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2022Graph neural networks for materials science and chemistrycited by 182
- 2019Explainability Techniques for Graph Convolutional Networkscited by 161
- 2017Towards better understanding of gradient-based attribution methods for Deep Neural Networkscited by 54
- 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
- 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
- 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
- 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
- 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 17
- 2020Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsificationcited by 16
- 2024Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanationscited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.