RegTrieve: Reducing System-Level Regression Errors for Machine Learning Systems via Retrieval-Enhanced Ensemble
Abstract
Multiple machine learning (ML) models are often incorporated into real-world ML systems. However, updating an individual model in these ML systems frequently results in regression errors, where the new model performs worse than the old model for some inputs. While model-level regression errors have been widely studied, little is known about how regression errors propagate at system level. To address this gap, we propose R eg T rieve , a novel retrieval-enhanced ensemble approach to reduce regression errors at both model and system level. Our evaluation across various model update scenarios shows that R eg T rieve reduces system-level regression errors with almost no impact on system accuracy, outperforming all baselines by 20.43% on average.
BibTeX
@article{Cao-al:FSE25,
author = {Junming Cao and
Xuwen Xiang and
Mingfei Cheng and
Bihuan Chen and
Xinyan Wang and
You Lu and
Chaofeng Sha and
Xiaofei Xie and
Xin Peng},
title = {{RegTrieve:} Reducing {System-Level} Regression Errors for Machine Learning Systems via {Retrieval-Enhanced} Ensemble},
journal = {{PACMSE}},
volume = {2},
number = {{FSE}},
pages = {1960--1982},
year = {2025},
}