EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods
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_ | 1866909207640408064 |
|---|---|
| author | Clark, Benedict Wilming, Rick Dox, Artur Eschenbach, Paul Hached, Sami Wodke, Daniel Jin Zewdie, Michias Taye Bruila, Uladzislau Oliveira, Marta Schulz, Hjalmar Cornils, Luca Matteo Panknin, Danny Boubekki, Ahcène Haufe, Stefan |
| author_facet | Clark, Benedict Wilming, Rick Dox, Artur Eschenbach, Paul Hached, Sami Wodke, Daniel Jin Zewdie, Michias Taye Bruila, Uladzislau Oliveira, Marta Schulz, Hjalmar Cornils, Luca Matteo Panknin, Danny Boubekki, Ahcène Haufe, Stefan |
| contents | The evolving landscape of explainable artificial intelligence (XAI) aims to improve the interpretability of intricate machine learning (ML) models, yet faces challenges in formalisation and empirical validation, being an inherently unsupervised process. In this paper, we bring together various benchmark datasets and novel performance metrics in an initial benchmarking platform, the Explainable AI Comparison Toolkit (EXACT), providing a standardised foundation for evaluating XAI methods. Our datasets incorporate ground truth explanations for class-conditional features, and leveraging novel quantitative metrics, this platform assesses the performance of post-hoc XAI methods in the quality of the explanations they produce. Our recent findings have highlighted the limitations of popular XAI methods, as they often struggle to surpass random baselines, attributing significance to irrelevant features. Moreover, we show the variability in explanations derived from different equally performing model architectures. This initial benchmarking platform therefore aims to allow XAI researchers to test and assure the high quality of their newly developed methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12261 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods Clark, Benedict Wilming, Rick Dox, Artur Eschenbach, Paul Hached, Sami Wodke, Daniel Jin Zewdie, Michias Taye Bruila, Uladzislau Oliveira, Marta Schulz, Hjalmar Cornils, Luca Matteo Panknin, Danny Boubekki, Ahcène Haufe, Stefan Machine Learning Artificial Intelligence The evolving landscape of explainable artificial intelligence (XAI) aims to improve the interpretability of intricate machine learning (ML) models, yet faces challenges in formalisation and empirical validation, being an inherently unsupervised process. In this paper, we bring together various benchmark datasets and novel performance metrics in an initial benchmarking platform, the Explainable AI Comparison Toolkit (EXACT), providing a standardised foundation for evaluating XAI methods. Our datasets incorporate ground truth explanations for class-conditional features, and leveraging novel quantitative metrics, this platform assesses the performance of post-hoc XAI methods in the quality of the explanations they produce. Our recent findings have highlighted the limitations of popular XAI methods, as they often struggle to surpass random baselines, attributing significance to irrelevant features. Moreover, we show the variability in explanations derived from different equally performing model architectures. This initial benchmarking platform therefore aims to allow XAI researchers to test and assure the high quality of their newly developed methods. |
| title | EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.12261 |