Xuwen Xiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuwen Xiang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Bihuan Chen
Fudan University, China
1 shared publication - Chaofeng Sha
Fudan University, Shanghai, China
1 shared publication - Junming Cao
Fudan University, China
1 shared publication - Mingfei Cheng
Singapore Management University, Singapore, Singapore
1 shared publication - Xiaofei Xie
Singapore Management University, Singapore, Singapore
1 shared publication - Xin Peng
Fudan University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 1960-1982
RegTrieve: Reducing System-Level Regression Errors for Machine Learning Systems via Retrieval-Enhanced Ensemble
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.
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 1960-1982
Open AccessRegTrieve: Reducing System-Level Regression Errors for Machine Learning Systems via Retrieval-Enhanced Ensemble
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.