Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918041610092544 |
|---|---|
| author | Zhang, Jiaxing Liu, Xiaoou Luo, Dongsheng Wei, Hua |
| author_facet | Zhang, Jiaxing Liu, Xiaoou Luo, Dongsheng Wei, Hua |
| contents | Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their predictions. While numerous post-hoc instance-level explanation methods have been proposed to interpret GNN predictions, the reliability of these explanations remains uncertain, particularly in the out-of-distribution or unknown test datasets. In this paper, we address this challenge by introducing an explainer framework with the confidence scoring module ( ConfExplainer), grounded in theoretical principle, which is generalized graph information bottleneck with confidence constraint (GIB-CC), that quantifies the reliability of generated explanations. Experimental results demonstrate the superiority of our approach, highlighting the effectiveness of the confidence score in enhancing the trustworthiness and robustness of GNN explanations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00437 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks Zhang, Jiaxing Liu, Xiaoou Luo, Dongsheng Wei, Hua Machine Learning Artificial Intelligence Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their predictions. While numerous post-hoc instance-level explanation methods have been proposed to interpret GNN predictions, the reliability of these explanations remains uncertain, particularly in the out-of-distribution or unknown test datasets. In this paper, we address this challenge by introducing an explainer framework with the confidence scoring module ( ConfExplainer), grounded in theoretical principle, which is generalized graph information bottleneck with confidence constraint (GIB-CC), that quantifies the reliability of generated explanations. Experimental results demonstrate the superiority of our approach, highlighting the effectiveness of the confidence score in enhancing the trustworthiness and robustness of GNN explanations. |
| title | Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.00437 |