Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.08198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911188345946112 |
|---|---|
| author | Fan, Wangxuan Li, Siqi Zhou, Doudou Okada, Yohei Hong, Chuan Liu, Molei Liu, Nan |
| author_facet | Fan, Wangxuan Li, Siqi Zhou, Doudou Okada, Yohei Hong, Chuan Liu, Molei Liu, Nan |
| contents | Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV) methods provide a principled framework for feature attribution in complex models but incur high computational costs, limiting their scalability in high-dimensional settings. We propose Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley), a stable and efficient SV approximation method inspired by stochastic optimization. We analyze variance theoretically, prove linear $Q$-convergence, and demonstrate improved empirical stability and low bias in practice on real-world datasets. In our numerical experiments, SIM-Shapley reduces computation time by up to 85% relative to state-of-the-art baselines while maintaining comparable feature attribution quality. Beyond feature attribution, our stochastic mini-batch iterative framework extends naturally to a broader class of sample average approximation problems, offering a new avenue for improving computational efficiency with stability guarantees. Code is publicly available at https://github.com/nliulab/SIM-Shapley. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08198 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation Fan, Wangxuan Li, Siqi Zhou, Doudou Okada, Yohei Hong, Chuan Liu, Molei Liu, Nan Machine Learning Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV) methods provide a principled framework for feature attribution in complex models but incur high computational costs, limiting their scalability in high-dimensional settings. We propose Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley), a stable and efficient SV approximation method inspired by stochastic optimization. We analyze variance theoretically, prove linear $Q$-convergence, and demonstrate improved empirical stability and low bias in practice on real-world datasets. In our numerical experiments, SIM-Shapley reduces computation time by up to 85% relative to state-of-the-art baselines while maintaining comparable feature attribution quality. Beyond feature attribution, our stochastic mini-batch iterative framework extends naturally to a broader class of sample average approximation problems, offering a new avenue for improving computational efficiency with stability guarantees. Code is publicly available at https://github.com/nliulab/SIM-Shapley. |
| title | SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.08198 |