arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.01460cs.DBcs.LG
收藏

数据解析中Shapley值的综合研究

A Comprehensive Study of Shapley Value in Data Analytics

The State Key Laboratory of Blockchain;Data Security, Zhejiang University;School of Computer Science \& Technology, Beijing Institute of Technology;State Key Laboratory of Blockchain;Data Security, Zhejiang University Beijing Institute of Technology

Hong Lin, Shixin Wan, Zhongle Xie, Ke Chen, Meihui Zhang, Lidan Shou, Gang Chen

AI总结:

本文首次全面研究数据解析中Shapley值的应用,归纳四大挑战并分析解决技术,实现开源框架SVBench并评估,指出当前局限及未来方向。

摘要:

近年来,Shapley值(SV)作为合作博弈论中的一个解概念,在数据解析(DA)中找到了众多应用。本文首次对贯穿DA工作流程的SV使用进行了全面研究,阐明了定义适用于DA的SV的关键变量,以及SV能为数据科学家提供的基本功能。我们归纳了在DA中使用SV的四个主要挑战,即计算效率、近似误差、隐私保护和可解释性,梳理了该领域现有技术中的解决方案,然后针对每个挑战及挑战之间的潜在冲突进行分析和讨论。我们还实现了SVBench,一个模块化且可扩展的开源框架,用于在不同DA任务中开发SV应用,并进行了广泛的评估以验证我们的分析和讨论。基于定性和定量结果,我们指出了当前将SV应用于DA的努力的局限性,并强调了未来研究和工程的方向。

英文摘要:

Over the recent years, Shapley value (SV), a solution concept from cooperative game theory, has found numerous applications in data analytics (DA). This paper presents the first comprehensive study of SV used throughout the DA workflow, clarifying the key variables in defining DA-applicable SV and the essential functionalities that SV can provide for data scientists. We condense four primary challenges of using SV in DA, namely computation efficiency, approximation error, privacy preservation, and interpretability, disentangle the resolution techniques from existing arts in this field, then analyze and discuss the techniques w.r.t. each challenge and the potential conflicts between challenges.We also implement SVBench, a modular and extensible open-source framework for developing SV applications in different DA tasks, and conduct extensive evaluations to validate our analyses and discussions. Based on the qualitative and quantitative results, we identify the limitations of current efforts for applying SV to DA and highlight the directions of future research and engineering.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑