Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2311.01010 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917672930770944 |
|---|---|
| author | Zhang, Borui Tian, Baotong Zheng, Wenzhao Zhou, Jie Lu, Jiwen |
| author_facet | Zhang, Borui Tian, Baotong Zheng, Wenzhao Zhou, Jie Lu, Jiwen |
| contents | Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity as the number of features increases. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. In our analysis of existing approaches, we observe that stochastic estimators can be unified as a linear transformation of randomly summed values from feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_01010 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fast Shapley Value Estimation: A Unified Approach Zhang, Borui Tian, Baotong Zheng, Wenzhao Zhou, Jie Lu, Jiwen Machine Learning Computer Vision and Pattern Recognition Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity as the number of features increases. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. In our analysis of existing approaches, we observe that stochastic estimators can be unified as a linear transformation of randomly summed values from feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values. |
| title | Fast Shapley Value Estimation: A Unified Approach |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.01010 |