Taxonomy of real faults in deep learning systems
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance. In this paper we introduce a large taxonomy of faults in deep learning (DL) systems. We have manually analysed 1059 artefacts gathered from GitHub commits and issues of projects that use the most popular DL frameworks (TensorFlow, Keras and PyTorch) and from related Stack Overflow posts. Structured interviews with 20 researchers and practitioners describing the problems they have encountered in their experience have enriched our taxonomy with a variety of additional faults that did not emerge from the other two sources. Our final taxonomy was validated with a survey involving an additional set of 21 developers, confirming that almost all fault categories (13/15) were experienced by at least 50% of the survey participants.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Qualitative methods in empirical studies of software engineering
Seaman, C. B. (1999) · IEEE Transactions on Software Engineering · doi:10.1109/32.799955 · Cited by 1,493
Is mutation an appropriate tool for testing experiments?
Andrews, J. H., Briand, L. C., & Labiche, Y. (2005) · Proceedings of the 27th international conference on Software engineering - ICSE '05 · doi:10.1145/1062455.1062530 · Cited by 777
Are mutants a valid substitute for real faults in software testing?
Just, R., Jalali, D., Inozemtseva, L., Ernst, M. D., Holmes, R., & Fraser, G. (2014) · Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering · doi:10.1145/2635868.2635929 · Cited by 595
Populating a Release History Database from version control and bug tracking systems
Fischer, M., Pinzger, M., & Gall, H. (2004) · International Conference on Software Maintenance, 2003. ICSM 2003. Proceedings. · doi:10.1109/icsm.2003.1235403 · Cited by 525
DeepMutation: Mutation Testing of Deep Learning Systems
Ma, L., Zhang, F., Sun, J., Xue, M., Li, B., Juefei-Xu, F., Xie, C., Li, L., Liu, Y., Zhao, J., et al. (2018) · 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre.2018.00021 · Cited by 366
Experiences from Conducting Semi-structured Interviews in Empirical Software Engineering Research
Hove, S. E., & Anda, B. (2005) · 11th IEEE International Software Metrics Symposium (METRICS'05) · doi:10.1109/metrics.2005.24 · Cited by 345
Software System Testing and Quality Assurance
Beizer, B. (1984) · Medical Entomology and Zoology · Cited by 315
A comprehensive study on deep learning bug characteristics
Islam, M. J., Nguyen, G., Pan, R., & Rajan, H. (2019) · Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3338906.3338955 · Cited by 305
An empirical study on TensorFlow program bugs
Zhang, Y., Chen, Y., Cheung, S.-C., Xiong, Y., & Zhang, L. (2018) · Proceedings of the 27th ACM SIGSOFT International Symposium on Software Testing and Analysis · doi:10.1145/3213846.3213866 · Cited by 304
Lwakatare, L. E., Raj, A., Bosch, J., Olsson, H. H., & Crnkovic, I. (2019) · Lecture Notes in Business Information Processing · doi:10.1007/978-3-030-19034-7_14 · Cited by 214
Software Engineering Challenges of Deep Learning
Arpteg, A., Brinne, B., Crnkovic-Friis, L., & Bosch, J. (2018) · 2018 44th Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa.2018.00018 · Cited by 201
Usman, M., Britto, R., Börstler, J., & Mendes, E. (2017) · Information and Software Technology · doi:10.1016/j.infsof.2017.01.006 · Cited by 173
Software error analysis: a real case study involving real faults and mutations
Daran, M., & Thévenod-Fosse, P. (1996) · ACM SIGSOFT Software Engineering Notes · doi:10.1145/226295.226313 · Cited by 171
An Empirical Study of Bugs in Machine Learning Systems
Thung, F., Wang, S., Lo, D., & Jiang, L. (2012) · 2012 IEEE 23rd International Symposium on Software Reliability Engineering · doi:10.1109/issre.2012.22 · Cited by 147
Organizing Knowledge: An Introduction to Managing Access to Information
Rowley, J., & Hartley, R. J. (2000) · Cited by 135
Seaman, C. B., Shull, F. J., Regardie, M., Elbert, D., Feldmann, R. L., Guo, Y., & Godfrey, S. (2008) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/1414004.1414030 · Cited by 77
An Empirical Study on Real Bugs for Machine Learning Programs
Sun, X., Zhou, T., Li, G., Hu, J., Yang, H. M., & Li, B. (2017) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec.2017.41 · Cited by 72
MuNN: Mutation Analysis of Neural Networks
Shen, W., Wan, J., & Chen, Z. (2018) · 2018 IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c.2018.00032 · Cited by 70
Crowdsourced Knowledge on Stack Overflow: A Systematic Mapping Study
Meldrum, S., Licorish, S. A., & Savarimuthu, B. T. R. (2017) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3084226.3084267 · Cited by 54
Cited by
Sampling in software engineering research: a critical review and guidelines
Baltes, S., & Ralph, P. (2022) · Empirical Software Engineering · doi:10.1007/s10664-021-10072-8 · Cited by 382
Testing machine learning based systems: a systematic mapping
Riccio, V., Jahangirova, G., Stocco, A., Humbatova, N., Weiss, M., & Tonella, P. (2020) · Empirical Software Engineering · doi:10.1007/s10664-020-09881-0 · Cited by 251
“The code that builds the MLS may be bug-free, but it might still deviate from the expected behaviour due to faults introduced in the training phase, such as the misconfiguration of some learning parameters or the use of an unbalanced/non-representative training set [97,100].”
BackgroundSelf-citationGiray, G. (2021) · Journal of Systems and Software · doi:10.1016/j.jss.2021.111031 · Cited by 187
A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research
Watson, C., Cooper, N., Palacio, D. N., Moran, K., & Poshyvanyk, D. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3485275 · Cited by 137
“However, they also learned that developers typically found that such errors require a relatively low amount of effort to fix [79].”
BackgroundGenerative Models for Effective ML on Private, Decentralized Datasets
Augenstein, S., McMahan, H. B., Ramage, D., Ramaswamy, S., Kairouz, P., Chen, M., Mathews, R., & Arcas, B. A. Y. (2019) · arXiv · doi:10.48550/arxiv.1911.06679 · Cited by 103
“Independently, Humbatova et al. (2019) identifies ‘text segmentation’ and ‘pixel encoding’ as being very common sources of bugs.”
BackgroundMethod
Metadata
- Authors
- Humbatova, N., Jahangirova, G., Bavota, G., Riccio, V., Stocco, A., & Tonella, P.
- Venue
- Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering
- Publisher
- ACM
- Published
- 2020-06-27
- Pages
- 1110-1121
- OpenAlex
- W3090643686
- Cited by
- 291
- References
- 19
- FWCI
- 30.76
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.