跳到主要导航 跳到搜索 跳到主要内容

Variance reduced Shapley value estimation for trustworthy data valuation

  • Xi'an Jiaotong University
  • Virginia Polytechnic Institute and State University
  • Institute for Interdisciplinary Information Core Technology
  • Southern University of Science and Technology

科研成果: 期刊稿件文章同行评审

16 引用 (Scopus)

摘要

Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios. The most widely used method is to define the data Shapley and approximate it by means of the permutation sampling algorithm. To make up for the large estimation variance of the permutation sampling that hinders the development of the data marketplace, we propose a more robust data valuation method using stratified sampling, named variance reduced data Shapley (VRDS for short). We theoretically show how to stratify, how many samples are taken at each stratum, and the sample complexity analysis of VRDS. Finally, the effectiveness of VRDS is illustrated in different types of datasets and data removal applications.

源语言英语
文章编号106305
期刊Computers and Operations Research
159
DOI
出版状态已出版 - 11月 2023

学术指纹

探究 'Variance reduced Shapley value estimation for trustworthy data valuation' 的科研主题。它们共同构成独一无二的指纹。

引用此