← 研踪 PaperTrailarXiv:2611.21504 · v1
Leverage-Enhanced Sampling Owen Method for Explainable Artificial Intelligence
首次提交 2026-11-17 02:02
版本更新 2026-11-17 02:02
雷达观测 2026-11-17 16:10
摘要
Recently, the Shapley value has been widely applied in machine learning for feature importance analysis and model explainability. The multilinear extension of games proposed by Owen (1972) expresses the Shapley value as the integral of partial derivatives along the main diagonal of the cube. Direct evaluation of this integral requires exponential-time computation of the partial derivatives. To improve computational efficiency, we propose a sampling-based estimation strategy within Owen's multilinear extension framework, combining stratified sampling with coalition leverage scores. Experimental results demonstrate that the proposed method significantly reduces computational costs while maintaining explanation accuracy.
作者备注:25 pages, 6 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 02:02 · 最新观测版本
Leverage-Enhanced Sampling Owen Method for Explainable Artificial Intelligence
Recently, the Shapley value has been widely applied in machine learning for feature importance analysis and model explainability. The multilinear extension of games proposed by Owen (1972) expresses the Shapley value as the integral of partial derivatives along the main diagonal of the cube. Direct evaluation of this integral requires exponential-time computation of the partial derivatives. To improve computational efficiency, we propose a sampling-based estimation strategy within Owen's multilinear extension framework, combining stratified sampling with coalition leverage scores. Experimental results demonstrate that the proposed method significantly reduces computational costs while maintaining explanation accuracy.
查看此版本解读 →查看此版本原文 ↗