Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2025
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 RegTrieve, 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 RegTrieve reduces system-level regression errors with almost no impact on system accuracy, outperforming all baselines by 20.43% on average.
Keywords
Regression Error, Ensemble Model, Spoken QA System
Discipline
Artificial Intelligence and Robotics | Software Engineering
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
Proceedings of the ACM on Software Engineering, Volume 2, Issue FSE, Trondheim, Norway, 2025 June 23-27
First Page
1960
Last Page
1982
Identifier
10.1145/3729358
Publisher
ACM
City or Country
New York
Citation
CAO, Junming; XIANG, Xuwen; CHENG, Mingfei; CHEN, Bihuan; WANG, Xinyan; LU, You; SHA, Chaofeng; Xiaofei XIE; and PENG, Xin.
RegTrieve: Reducing system-level regression errors for machine learning systems via retrieval-enhanced ensemble. (2025). Proceedings of the ACM on Software Engineering, Volume 2, Issue FSE, Trondheim, Norway, 2025 June 23-27. 1960-1982.
Available at: https://ink.library.smu.edu.sg/sis_research/10325
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3729358