# A Comprehensive Study of Deep Learning Model Fixing Approaches

arXiv: https://arxiv.org/abs/2512.23745 · HTML: https://mlsanity.com/paper/2512.23745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 81 references that are in the map.
- First posted on arXiv 26 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Neuron Shapley: Discovering the Responsible Neurons](https://mlsanity.com/paper/2002.09815/) (2020)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems](https://mlsanity.com/paper/1812.10812/) (2018)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [An Alternative Surrogate Loss for PGD-based Adversarial Testing](https://mlsanity.com/paper/1910.09338/) (2019)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [Facial expression and attributes recognition based on multi-task learning of lightweight neural networks](https://mlsanity.com/paper/2103.17107/) (2021)
- [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)
- [NNrepair: Constraint-based Repair of Neural Network Classifiers](https://mlsanity.com/paper/2103.12535/) (2021)
- [Neural Network Repair with Reachability Analysis](https://mlsanity.com/paper/2108.04214/) (2021)
- [Towards Repairing Neural Networks Correctly](https://mlsanity.com/paper/2012.01872/) (2020)
- [Sound and Complete Neural Network Repair with Minimality and Locality Guarantees](https://mlsanity.com/paper/2110.07682/) (2021)
- [Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning](https://mlsanity.com/paper/2002.00863/) (2020)
- [Architecture-Preserving Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2304.03496/) (2023)
- [Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2410.13110/) (2024)
- [NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History](https://mlsanity.com/paper/2203.00191/) (2022)
- [ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks](https://mlsanity.com/paper/2111.13330/) (2021)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [Certified Continual Learning for Neural Network Regression](https://mlsanity.com/paper/2407.06697/) (2024)
- [AIREPAIR: A Repair Platform for Neural Networks](https://mlsanity.com/paper/2211.15387/) (2022)
- [A Survey of Reinforcement Learning for Software Engineering](https://mlsanity.com/paper/2507.12483/) (2025)

## Built on by (most cited first, 2 of 2)

- [RepTran: Search-Based Repair of Transformer Models](https://mlsanity.com/paper/2607.11193/) (2026)
- [Evaluating Fuzz Testing for Reinforcement Learning Agents](https://mlsanity.com/paper/2607.24577/) (2026)

## Abstract (arXiv)

Deep Learning (DL) has been widely adopted in diverse industrial domains, including autonomous driving, intelligent healthcare, and aided programming. Like traditional software, DL systems are also prone to faults, whose malfunctioning may expose users to significant risks. Consequently, numerous approaches have been proposed to address these issues. In this paper, we conduct a large-scale empirical study on 16 state-of-the-art DL model fixing approaches, spanning model-level, layer-level, and neuron-level categories, to comprehensively evaluate their performance. We assess not only their fixing effectiveness (their primary purpose) but also their impact on other critical properties, such as robustness, fairness, and backward compatibility. To ensure comprehensive and fair evaluation, we employ a diverse set of datasets, model architectures, and application domains within a uniform experimental setup for experimentation. We summarize several key findings with implications for both industry and academia. For example, model-level approaches demonstrate superior fixing effectiveness compared to others. No single approach can achieve the best fixing performance while improving accuracy and maintaining all other properties. Thus, academia should prioritize research on mitigating these side effects. These insights highlight promising directions for future exploration in this field.