# On Accelerating Deep Neural Network Mutation Analysis by Neuron and Mutant Clustering

arXiv: https://arxiv.org/abs/2501.12598 · HTML: https://mlsanity.com/paper/2501.12598/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [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)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [DeepMutation: Mutation Testing of Deep Learning Systems](https://mlsanity.com/paper/1805.05206/) (2018)
- [Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing](https://mlsanity.com/paper/1812.05793/) (2018)
- [Arachne: Search Based Repair of Deep Neural Networks](https://mlsanity.com/paper/1912.12463/) (2019)
- [A Search-Based Testing Framework for Deep Neural Networks of Source Code Embedding](https://mlsanity.com/paper/2101.07910/) (2021)
- [DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score](https://mlsanity.com/paper/2109.07514/) (2021)
- [Neural Software Analysis](https://mlsanity.com/paper/2011.07986/) (2020)
- [Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation](https://mlsanity.com/paper/2207.10942/) (2022)
- [Hierarchical Agglomerative Graph Clustering in Poly-Logarithmic Depth](https://mlsanity.com/paper/2206.11654/) (2022)
- [Patching Weak Convolutional Neural Network Models through Modularization and Composition](https://mlsanity.com/paper/2209.06116/) (2022)
- [Mutation-based Fault Localization of Deep Neural Networks](https://mlsanity.com/paper/2309.05067/) (2023)
- [muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults](https://mlsanity.com/paper/2408.15150/) (2024)
- [Reusing Convolutional Neural Network Models through Modularization and Composition](https://mlsanity.com/paper/2311.04438/) (2023)

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

- [Quality-Driven Selective Mutation for Deep Learning](https://mlsanity.com/paper/2604.22640/) (2026)

## Abstract (arXiv)

Mutation analysis of deep neural networks (DNNs) is a promising method for effective evaluation of test data quality and model robustness, but it can be computationally expensive, especially for large models. To alleviate this, we present DEEPMAACC, a technique and a tool that speeds up DNN mutation analysis through neuron and mutant clustering. DEEPMAACC implements two methods: (1) neuron clustering to reduce the number of generated mutants and (2) mutant clustering to reduce the number of mutants to be tested by selecting representative mutants for testing. Both use hierarchical agglomerative clustering to group neurons and mutants with similar weights, with the goal of improving efficiency while maintaining mutation score. DEEPMAACC has been evaluated on 8 DNN models across 4 popular classification datasets and two DNN architectures. When compared to exhaustive, or vanilla, mutation analysis, the results provide empirical evidence that neuron clustering approach, on average, accelerates mutation analysis by 69.77%, with an average -26.84% error in mutation score. Meanwhile, mutant clustering approach, on average, accelerates mutation analysis by 35.31%, with an average 1.96% error in mutation score. Our results demonstrate that a trade-off can be made between mutation testing speed and mutation score error.