Causality-Aware Local Interpretable Model-Agnostic Explanations
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916438828122112 |
|---|---|
| author | Cinquini, Martina Guidotti, Riccardo |
| author_facet | Cinquini, Martina Guidotti, Riccardo |
| contents | A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects on randomly generated feature values that may rarely occur in the original samples. This paper addresses this issue by integrating causal knowledge in an XAI method to enhance transparency and enable users to assess the quality of the generated explanations. Specifically, we propose a novel extension to a widely used local and model-agnostic explainer, which encodes explicit causal relationships within the data surrounding the instance being explained. Extensive experiments show that our approach overcomes the original method in terms of faithfully replicating the black-box model's mechanism and the consistency and reliability of the generated explanations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_05256 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Causality-Aware Local Interpretable Model-Agnostic Explanations Cinquini, Martina Guidotti, Riccardo Artificial Intelligence Machine Learning A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects on randomly generated feature values that may rarely occur in the original samples. This paper addresses this issue by integrating causal knowledge in an XAI method to enhance transparency and enable users to assess the quality of the generated explanations. Specifically, we propose a novel extension to a widely used local and model-agnostic explainer, which encodes explicit causal relationships within the data surrounding the instance being explained. Extensive experiments show that our approach overcomes the original method in terms of faithfully replicating the black-box model's mechanism and the consistency and reliability of the generated explanations. |
| title | Causality-Aware Local Interpretable Model-Agnostic Explanations |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2212.05256 |