Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
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_ | 1866915395302064128 |
|---|---|
| author | Zhu, Chenrui Bounia, Louenas Nguyen, Vu Linh Destercke, Sébastien Hoarau, Arthur |
| author_facet | Zhu, Chenrui Bounia, Louenas Nguyen, Vu Linh Destercke, Sébastien Hoarau, Arthur |
| contents | Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12913 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI Zhu, Chenrui Bounia, Louenas Nguyen, Vu Linh Destercke, Sébastien Hoarau, Arthur Machine Learning Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios. |
| title | Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.12913 |