# QNNRepair: Quantized Neural Network Repair

arXiv: https://arxiv.org/abs/2306.13793 · HTML: https://mlsanity.com/paper/2306.13793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 23 Jun 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Safety Verification of Deep Neural Networks](https://mlsanity.com/paper/1610.06940/) (2016)
- [Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks](https://mlsanity.com/paper/1705.01320/) (2017)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification](https://mlsanity.com/paper/2103.06624/) (2021)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [A Survey on Methods and Theories of Quantized Neural Networks](https://mlsanity.com/paper/1808.04752/) (2018)
- [The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results](https://mlsanity.com/paper/2109.00498/) (2021)
- [TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing](https://mlsanity.com/paper/1807.10875/) (2018)
- [An Abstraction-Based Framework for Neural Network Verification](https://mlsanity.com/paper/1910.14574/) (2019)
- [SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation](https://mlsanity.com/paper/2202.07471/) (2022)
- [Concolic Testing for Deep Neural Networks](https://mlsanity.com/paper/1805.00089/) (2018)
- [An SMT-Based Approach for Verifying Binarized Neural Networks](https://mlsanity.com/paper/2011.02948/) (2020)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [DeepFault: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/1902.05974/) (2019)
- [Scalable Verification of Quantized Neural Networks (Technical Report)](https://mlsanity.com/paper/2012.08185/) (2020)
- [NNrepair: Constraint-based Repair of Neural Network Classifiers](https://mlsanity.com/paper/2103.12535/) (2021)
- [DeepCorrect: Correcting DNN models against Image Distortions](https://mlsanity.com/paper/1705.02406/) (2017)
- [Testing and verification of neural-network-based safety-critical control software: A systematic literature review](https://mlsanity.com/paper/1910.06715/) (2019)
- [QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks](https://mlsanity.com/paper/2212.11138/) (2022)
- [Improving Adversarial Robustness in Weight-quantized Neural Networks](https://mlsanity.com/paper/2012.14965/) (2020)
- [Verifying Quantized Neural Networks using SMT-Based Model Checking](https://mlsanity.com/paper/2106.05997/) (2021)
- [QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checking](https://mlsanity.com/paper/2111.13110/) (2021)

## Abstract (arXiv)

We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized neural networks and a repair dataset of passing and failing tests. At first, QNNRepair applies a software fault localization method to identify the neurons that cause performance degradation during neural network quantization. Then, it formulates the repair problem into a linear programming problem of solving neuron weights parameters, which corrects the QNN's performance on failing tests while not compromising its performance on passing tests. We evaluate QNNRepair with widely used neural network architectures such as MobileNetV2, ResNet, and VGGNet on popular datasets, including high-resolution images. We also compare QNNRepair with the state-of-the-art data-free quantization method SQuant. According to the experiment results, we conclude that QNNRepair is effective in improving the quantized model's performance in most cases. Its repaired models have 24% higher accuracy than SQuant's in the independent validation set, especially for the ImageNet dataset.