On the Robustness of Post-hoc GNN Explainers to Label Noise
Not on the map. Why?
Abstract (arXiv)
Proposed as a solution to the inherent black-box limitations of graph neural networks (GNNs), post-hoc GNN explainers aim to provide precise and insightful explanations of the behaviours exhibited by trained GNNs. Despite their recent notable advancements in academic and industrial contexts, the robustness of post-hoc GNN explainers remains unexplored when confronted with label noise. To bridge this gap, we conduct a systematic empirical investigation to evaluate the efficacy of diverse post-hoc GNN explainers under varying degrees of label noise. Our results reveal several key insights: Firstly, post-hoc GNN explainers are susceptible to label perturbations. Secondly, even minor levels of label noise, inconsequential to GNN performance, harm the quality of generated explanations substantially. Lastly, we engage in a discourse regarding the progressive recovery of explanation effectiveness with escalating noise levels.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 4 Sep 2023.
Builds on
21 of 23 references.
References · 21
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
- 2020Parameterized Explainer for Graph Neural Networkcited by 423
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
- 2018Adversarial Attack on Graph Structured Datacited by 300
- 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
- 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
- 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
9 more
- 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
- 2021Towards Self-Explainable Graph Neural Networkcited by 75
- 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
- 2019Certifiable Robustness to Graph Perturbationscited by 62
- 2022Theory of Graph Neural Networks: Representation and Learningcited by 60
- 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
- 2020Hierarchical Message-Passing Graph Neural Networkscited by 21
- 2023Knowledge-augmented Graph Machine Learning for Drug Discovery: A Surveycited by 6
- 2021The Burden of Being a Bridge: Analysing Subjective Well-Being of Twitter Users during the COVID-19 Pandemiccited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.