mlsanityData to 7 Oct 2026

DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs

arXiv 2112.04036 ↗First posted 7 Dec 2021cs.SE cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) are used in a wide variety of applications. However, as in any software application, DNN-based apps are afflicted with bugs. Previous work observed that DNN bug fix patterns are different from traditional bug fix patterns. Furthermore, those buggy models are non-trivial to diagnose and fix due to inexplicit errors with several options to fix them. To support developers in locating and fixing bugs, we propose DeepDiagnosis, a novel debugging approach that localizes the faults, reports error symptoms and suggests fixes for DNN programs. In the first phase, our technique monitors a training model, periodically checking for eight types of error conditions. Then, in case of problems, it reports messages containing sufficient information to perform actionable repairs to the model. In the evaluation, we thoroughly examine 444 models -53 real-world from GitHub and Stack Overflow, and 391 curated by AUTOTRAINER. DeepDiagnosis provides superior accuracy when compared to UMLUAT and DeepLocalize. Our technique is faster than AUTOTRAINER for fault localization. The results show that our approach can support additional types of models, while state-of-the-art was only able to handle classification ones. Our technique was able to report bugs that do not manifest as numerical errors during training. Also, it can provide actionable insights for fix whereas DeepLocalize can only report faults that lead to numerical errors during training. DeepDiagnosis manifests the best capabilities of fault detection, bug localization, and symptoms identification when compared to other approaches.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 15 of its 41 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

15 of 41 references.

References · 15

  1. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  2. 2018Stable Recurrent Modelscited by 65
  3. 2019A Comprehensive Study on Deep Learning Bug Characteristicscited by 65
  4. 2016Noisy Activation Functionscited by 53
  5. 2020Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairnesscited by 52
  6. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  7. 2021DeepLocalize: Fault Localization for Deep Neural Networkscited by 37
  8. 2020Repairing Deep Neural Networks: Fix Patterns and Challengescited by 33
  9. 2019DeepFault: Fault Localization for Deep Neural Networkscited by 29
  10. 2021The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Largecited by 17
  11. 2014Random Walk Initialization for Training Very Deep Feedforward Networkscited by 13
  12. 2016Revise Saturated Activation Functionscited by 11
3 more
  1. 2018Detecting Dead Weights and Units in Neural Networkscited by 7
  2. 2020The effect of Target Normalization and Momentum on Dying ReLUcited by 5
  3. 2021Manas: Mining Software Repositories to Assist AutoMLcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 4; 2024: 2; 2025: 6; 2026: 4.

19 papers.

Sort:

  1. 2022Bugs in Machine Learning-based Systems: A Faultload Benchmarkcited by 15
  2. 2023Bug Characterization in Machine Learning-based Systemscited by 10
  3. 2023Mutation-based Fault Localization of Deep Neural Networkscited by 5
  4. 2023Semantic-Based Neural Network Repaircited by 3
  5. 2025Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)cited by 3
  6. 2025Feature-Guided Analysis of Neural Networks: A Replication Studycited by 2
  7. 2024Toward Debugging Deep Reinforcement Learning Programs with RLExplorercited by 1
  8. 2025IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Modelscited by 1
  9. 2025An Experience Report on Regression-Free Repair of Deep Neural Network Modelcited by 1
  10. 2025Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networkscited by 1
  11. 2022A Retrospective on ICSE 2022cited by 0
  12. 2022Comparative analysis of real bugs in open-source Machine Learning projects -- A Registered Reportcited by 0
7 more
  1. 2023Path Analysis for Effective Fault Localization in Deep Neural Networkscited by 0
  2. 2024An Empirical Study of Fault Localisation Techniques for Deep Learningcited by 0
  3. 2025GAN-enhanced Simulation-driven DNN Testing in Absence of Ground Truthcited by 0
  4. 2026BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimizationcited by 0
  5. 2026Hierarchical Fault Detection and Diagnosis for Transformer Architecturescited by 0
  6. 2026Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programscited by 0
  7. 2026Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosiscited by 0