# An Experience Report on Regression-Free Repair of Deep Neural Network Model

arXiv: https://arxiv.org/abs/2503.07079 · HTML: https://mlsanity.com/paper/2503.07079/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Positive-Congruent Training: Towards Regression-Free Model Updates](https://mlsanity.com/paper/2011.09161/) (2020)
- [An Empirical Analysis of Backward Compatibility in Machine Learning Systems](https://mlsanity.com/paper/2008.04572/) (2020)
- [Arachne: Search Based Repair of Deep Neural Networks](https://mlsanity.com/paper/1912.12463/) (2019)
- [DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs](https://mlsanity.com/paper/2112.04036/) (2021)
- [NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History](https://mlsanity.com/paper/2203.00191/) (2022)

## Built on by (most cited first, 1 of 1)

- [RepTran: Search-Based Repair of Transformer Models](https://mlsanity.com/paper/2607.11193/) (2026)

## Abstract (arXiv)

Systems based on Deep Neural Networks (DNNs) are increasingly being used in industry. In the process of system operation, DNNs need to be updated in order to improve their performance. When updating DNNs, systems used in companies that require high reliability must have as few regressions as possible. Since the update of DNNs has a data-driven nature, it is difficult to suppress regressions as expected by developers. This paper identifies the requirements for DNN updating in industry and presents a case study using techniques to meet those requirements. In the case study, we worked on satisfying the requirement to update models trained on car images collected in Fujitsu assuming security applications without regression for a specific class. We were able to suppress regression by customizing the objective function based on NeuRecover, a DNN repair technique. Moreover, we discuss some of the challenges identified in the case study.