Generating Counterfactual Explanations Under Temporal Constraints
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909618542739456 |
|---|---|
| author | Buliga, Andrei Di Francescomarino, Chiara Ghidini, Chiara Montali, Marco Ronzani, Massimiliano |
| author_facet | Buliga, Andrei Di Francescomarino, Chiara Ghidini, Chiara Montali, Marco Ronzani, Massimiliano |
| contents | Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods do not readily apply to temporal domains, such as that of process mining, where data take the form of traces of activities that must obey to temporal background knowledge expressing which dynamics are possible and which not. Specifically, counterfactuals generated off-the-shelf may violate the background knowledge, leading to inconsistent explanations. This work tackles this challenge by introducing a novel approach for generating temporally constrained counterfactuals, guaranteed to comply by design with background knowledge expressed in Linear Temporal Logic on process traces (LTLp). We do so by infusing automata-theoretic techniques for LTLp inside a genetic algorithm for counterfactual generation. The empirical evaluation shows that the generated counterfactuals are temporally meaningful and more interpretable for applications involving temporal dependencies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01792 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generating Counterfactual Explanations Under Temporal Constraints Buliga, Andrei Di Francescomarino, Chiara Ghidini, Chiara Montali, Marco Ronzani, Massimiliano Artificial Intelligence Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods do not readily apply to temporal domains, such as that of process mining, where data take the form of traces of activities that must obey to temporal background knowledge expressing which dynamics are possible and which not. Specifically, counterfactuals generated off-the-shelf may violate the background knowledge, leading to inconsistent explanations. This work tackles this challenge by introducing a novel approach for generating temporally constrained counterfactuals, guaranteed to comply by design with background knowledge expressed in Linear Temporal Logic on process traces (LTLp). We do so by infusing automata-theoretic techniques for LTLp inside a genetic algorithm for counterfactual generation. The empirical evaluation shows that the generated counterfactuals are temporally meaningful and more interpretable for applications involving temporal dependencies. |
| title | Generating Counterfactual Explanations Under Temporal Constraints |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01792 |