|国家预印本平台
首页|On the Usage of Gaussian Process for Efficient Data Valuation

On the Usage of Gaussian Process for Efficient Data Valuation

On the Usage of Gaussian Process for Efficient Data Valuation

来源:Arxiv_logoArxiv
英文摘要

In machine learning, knowing the impact of a given datum on model training is a fundamental task referred to as Data Valuation. Building on previous works from the literature, we have designed a novel canonical decomposition allowing practitioners to analyze any data valuation method as the combination of two parts: a utility function that captures characteristics from a given model and an aggregation procedure that merges such information. We also propose to use Gaussian Processes as a means to easily access the utility function on ``sub-models'', which are models trained on a subset of the training set. The strength of our approach stems from both its theoretical grounding in Bayesian theory, and its practical reach, by enabling fast estimation of valuations thanks to efficient update formulae.

Clément Bénesse、Patrick Mesana、Athéna?s Gautier、Sébastien Gambs

计算技术、计算机技术

Clément Bénesse,Patrick Mesana,Athéna?s Gautier,Sébastien Gambs.On the Usage of Gaussian Process for Efficient Data Valuation[EB/OL].(2025-06-04)[2025-06-07].https://arxiv.org/abs/2506.04026.点此复制

评论