Even-if Explanations: Formal Foundations, Priorities and Complexity
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916256634896384 |
|---|---|
| author | Alfano, Gianvincenzo Greco, Sergio Mandaglio, Domenico Parisi, Francesco Shahbazian, Reza Trubitsyna, Irina |
| author_facet | Alfano, Gianvincenzo Greco, Sergio Mandaglio, Domenico Parisi, Francesco Shahbazian, Reza Trubitsyna, Irina |
| contents | EXplainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability queries attempt to answer why individual inputs are classified in a certain way by a given model. While there has been important work on counterfactual explanations, less attention has been devoted to semifactual ones. In this paper, we focus on local post-hoc explainability queries within the semifactual `even-if' thinking and their computational complexity among different classes of models, and show that both linear and tree-based models are strictly more interpretable than neural networks. After this, we introduce a preference-based framework that enables users to personalize explanations based on their preferences, both in the case of semifactuals and counterfactuals, enhancing interpretability and user-centricity. Finally, we explore the complexity of several interpretability problems in the proposed preference-based framework and provide algorithms for polynomial cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10938 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Even-if Explanations: Formal Foundations, Priorities and Complexity Alfano, Gianvincenzo Greco, Sergio Mandaglio, Domenico Parisi, Francesco Shahbazian, Reza Trubitsyna, Irina Artificial Intelligence Machine Learning EXplainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability queries attempt to answer why individual inputs are classified in a certain way by a given model. While there has been important work on counterfactual explanations, less attention has been devoted to semifactual ones. In this paper, we focus on local post-hoc explainability queries within the semifactual `even-if' thinking and their computational complexity among different classes of models, and show that both linear and tree-based models are strictly more interpretable than neural networks. After this, we introduce a preference-based framework that enables users to personalize explanations based on their preferences, both in the case of semifactuals and counterfactuals, enhancing interpretability and user-centricity. Finally, we explore the complexity of several interpretability problems in the proposed preference-based framework and provide algorithms for polynomial cases. |
| title | Even-if Explanations: Formal Foundations, Priorities and Complexity |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.10938 |