mlsanityData to 7 Oct 2026

Repairing Deep Neural Networks: Fix Patterns and Challenges

arXiv 2005.00972 ↗First posted 3 May 2020cs.SEcited by 33

Not on the map. Why?

Abstract (arXiv)

Significant interest in applying Deep Neural Network (DNN) has fueled the need to support engineering of software that uses DNNs. Repairing software that uses DNNs is one such unmistakable SE need where automated tools could be beneficial; however, we do not fully understand challenges to repairing and patterns that are utilized when manually repairing DNNs. What challenges should automated repair tools address? What are the repair patterns whose automation could help developers? Which repair patterns should be assigned a higher priority for building automated bug repair tools? This work presents a comprehensive study of bug fix patterns to address these questions. We have studied 415 repairs from Stack overflow and 555 repairs from Github for five popular deep learning libraries Caffe, Keras, Tensorflow, Theano, and Torch to understand challenges in repairs and bug repair patterns. Our key findings reveal that DNN bug fix patterns are distinctive compared to traditional bug fix patterns; the most common bug fix patterns are fixing data dimension and neural network connectivity; DNN bug fixes have the potential to introduce adversarial vulnerabilities; DNN bug fixes frequently introduce new bugs; and DNN bug localization, reuse of trained model, and coping with frequent releases are major challenges faced by developers when fixing bugs. We also contribute a benchmark of 667 DNN (bug, repair) instances.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 7; 2023: 9; 2024: 3; 2025: 2; 2026: 1.

33 papers.

Sort:

  1. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  2. 2021NNrepair: Constraint-based Repair of Neural Network Classifierscited by 24
  3. 2021An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applicationscited by 20
  4. 2021Neural Network Repair with Reachability Analysiscited by 19
  5. 2021DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programscited by 19
  6. 2021Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approachcited by 18
  7. 2022DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programscited by 16
  8. 2022Bugs in Machine Learning-based Systems: A Faultload Benchmarkcited by 15
  9. 2021Understanding Performance Problems in Deep Learning Systemscited by 12
  10. 2023Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Visioncited by 11
  11. 2021Design Smells in Deep Learning Programs: An Empirical Studycited by 10
  12. 2023Bug Characterization in Machine Learning-based Systemscited by 10
21 more
  1. 2021Automatic Fault Detection for Deep Learning Programs Using Graph Transformationscited by 9
  2. 2021Manas: Mining Software Repositories to Assist AutoMLcited by 5
  3. 2023OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networkscited by 5
  4. 2023Mutation-based Fault Localization of Deep Neural Networkscited by 5
  5. 2021NEUROSPF: A tool for the Symbolic Analysis of Neural Networkscited by 4
  6. 2023Semantic-Based Neural Network Repaircited by 3
  7. 2023Test & Evaluation Best Practices for Machine Learning-Enabled Systemscited by 3
  8. 2023FetaFix: Automatic Fault Localization and Repair of Deep Learning Model Conversionscited by 3
  9. 2022Challenges in Migrating Imperative Deep Learning Programs to Graph Execution: An Empirical Studycited by 2
  10. 2022What is Software Quality for AI Engineers? Towards a Thinning of the Fogcited by 2
  11. 2022Testing Feedforward Neural Networks Training Programscited by 2
  12. 2023What Kinds of Contracts Do ML APIs Need?cited by 2
  13. 2024Unraveling Code Clone Dynamics in Deep Learning Frameworkscited by 2
  14. 2022Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methodscited by 1
  15. 2024Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deploymentcited by 1
  16. 2022Repairing Group-Level Errors for DNNs Using Weighted Regularizationcited by 0
  17. 2023Causal Repair of Learning-enabled Cyber-physical Systemscited by 0
  18. 2024Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projectscited by 0
  19. 2025Speculative Automated Refactoring of Imperative Deep Learning Programs to Graph Executioncited by 0
  20. 2025GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworkscited by 0
  21. 2026Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programscited by 0