On the Evaluation Consistency of Attribution-based Explanations
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_ | 1866916338618859520 |
|---|---|
| author | Duan, Jiarui Li, Haoling Zhang, Haofei Jiang, Hao Xue, Mengqi Sun, Li Song, Mingli Song, Jie |
| author_facet | Duan, Jiarui Li, Haoling Zhang, Haofei Jiang, Hao Xue, Mengqi Sun, Li Song, Mingli Song, Jie |
| contents | Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and systematic investigations in prior literature impedes comprehensive evaluations of existing methodologies. In this work, we introduce {Meta-Rank}, an open platform for benchmarking attribution methods in the image domain. Presently, Meta-Rank assesses eight exemplary attribution methods using six renowned model architectures on four diverse datasets, employing both the \textit{Most Relevant First} (MoRF) and \textit{Least Relevant First} (LeRF) evaluation protocols. Through extensive experimentation, our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets. Our findings underscore the necessity for future research in this domain to conduct rigorous evaluations encompassing a broader range of models and datasets, and to reassess the assumptions underlying the empirical success of different attribution methods. Our code is publicly available at \url{https://github.com/TreeThree-R/Meta-Rank}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19471 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Evaluation Consistency of Attribution-based Explanations Duan, Jiarui Li, Haoling Zhang, Haofei Jiang, Hao Xue, Mengqi Sun, Li Song, Mingli Song, Jie Computer Vision and Pattern Recognition Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and systematic investigations in prior literature impedes comprehensive evaluations of existing methodologies. In this work, we introduce {Meta-Rank}, an open platform for benchmarking attribution methods in the image domain. Presently, Meta-Rank assesses eight exemplary attribution methods using six renowned model architectures on four diverse datasets, employing both the \textit{Most Relevant First} (MoRF) and \textit{Least Relevant First} (LeRF) evaluation protocols. Through extensive experimentation, our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets. Our findings underscore the necessity for future research in this domain to conduct rigorous evaluations encompassing a broader range of models and datasets, and to reassess the assumptions underlying the empirical success of different attribution methods. Our code is publicly available at \url{https://github.com/TreeThree-R/Meta-Rank}. |
| title | On the Evaluation Consistency of Attribution-based Explanations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.19471 |