# NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History

arXiv: https://arxiv.org/abs/2203.00191 · HTML: https://mlsanity.com/paper/2203.00191/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 10 of 10)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving](https://mlsanity.com/paper/1505.00256/) (2015)
- [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)
- [Elixir: Effective object-oriented program repair](https://mlsanity.com/paper/2112.10915/) (2021)

## Built on by (most cited first, 8 of 8)

- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting](https://mlsanity.com/paper/2401.10359/) (2024)
- [Certified Continual Learning for Neural Network Regression](https://mlsanity.com/paper/2407.06697/) (2024)
- [A Comprehensive Study of Deep Learning Model Fixing Approaches](https://mlsanity.com/paper/2512.23745/) (2025)
- [An Experience Report on Regression-Free Repair of Deep Neural Network Model](https://mlsanity.com/paper/2503.07079/) (2025)
- [Practical Insights of Repairing Model Problems on Image Classification](https://mlsanity.com/paper/2205.07116/) (2022)
- [Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap](https://mlsanity.com/paper/2505.19625/) (2025)
- [RepTran: Search-Based Repair of Transformer Models](https://mlsanity.com/paper/2607.11193/) (2026)

## Abstract (arXiv)

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key challenge comes from the little controllability in updating DNNs. Retraining to fix some behavior often has a destructive impact on other behavior, causing regressions, i.e., the updated DNN fails with inputs correctly handled by the original one. This problem is crucial when engineers are required to investigate failures in intensive assurance activities for safety or trust. Search-based repair techniques for DNNs have potentials to tackle this challenge by enabling localized updates only on "responsible parameters" inside the DNN. However, the potentials have not been explored to realize sufficient controllability to suppress regressions in DNN repair tasks. In this paper, we propose a novel DNN repair method that makes use of the training history for judging which DNN parameters should be changed or not to suppress regressions. We implemented the method into a tool called NeuRecover and evaluated it with three datasets. Our method outperformed the existing method by achieving often less than a quarter, even a tenth in some cases, number of regressions. Our method is especially effective when the repair requirements are tight to fix specific failure types. In such cases, our method showed stably low rates (<2%) of regressions, which were in many cases a tenth of regressions caused by retraining.