Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909207676059648 |
|---|---|
| author | Pascual-Triana, José Daniel Fernández, Alberto Del Ser, Javier Herrera, Francisco |
| author_facet | Pascual-Triana, José Daniel Fernández, Alberto Del Ser, Javier Herrera, Francisco |
| contents | Explainable Artificial Intelligence (XAI) is a pivotal research domain aimed at understanding the operational mechanisms of AI systems, particularly those considered ``black boxes'' due to their complex, opaque nature. XAI seeks to make these AI systems more understandable and trustworthy, providing insight into their decision-making processes. By producing clear and comprehensible explanations, XAI enables users, practitioners, and stakeholders to trust a model's decisions. This work analyses the value of data morphology strategies in generating counterfactual explanations. It introduces the Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF) method, a model-agnostic counterfactual generator that leverages data morphology to estimate a model's decision boundaries. The ONB-MACF method constructs hyperspheres in the data space whose covered points share a class, mapping the decision boundary. Counterfactuals are then generated by incrementally adjusting an instance's attributes towards the nearest alternate-class hypersphere, crossing the decision boundary with minimal modifications. By design, the ONB-MACF method generates feasible and sparse counterfactuals that follow the data distribution. Our comprehensive benchmark from a double perspective (quantitative and qualitative) shows that the ONB-MACF method outperforms existing state-of-the-art counterfactual generation methods across multiple quality metrics on diverse tabular datasets. This supports our hypothesis, showcasing the potential of data-morphology-based explainability strategies for trustworthy AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12326 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence Pascual-Triana, José Daniel Fernández, Alberto Del Ser, Javier Herrera, Francisco Machine Learning Explainable Artificial Intelligence (XAI) is a pivotal research domain aimed at understanding the operational mechanisms of AI systems, particularly those considered ``black boxes'' due to their complex, opaque nature. XAI seeks to make these AI systems more understandable and trustworthy, providing insight into their decision-making processes. By producing clear and comprehensible explanations, XAI enables users, practitioners, and stakeholders to trust a model's decisions. This work analyses the value of data morphology strategies in generating counterfactual explanations. It introduces the Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF) method, a model-agnostic counterfactual generator that leverages data morphology to estimate a model's decision boundaries. The ONB-MACF method constructs hyperspheres in the data space whose covered points share a class, mapping the decision boundary. Counterfactuals are then generated by incrementally adjusting an instance's attributes towards the nearest alternate-class hypersphere, crossing the decision boundary with minimal modifications. By design, the ONB-MACF method generates feasible and sparse counterfactuals that follow the data distribution. Our comprehensive benchmark from a double perspective (quantitative and qualitative) shows that the ONB-MACF method outperforms existing state-of-the-art counterfactual generation methods across multiple quality metrics on diverse tabular datasets. This supports our hypothesis, showcasing the potential of data-morphology-based explainability strategies for trustworthy AI. |
| title | Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligence |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.12326 |