Repairing Deep Neural Networks: Fix Patterns and Challenges

Thumbnail Image
Date
2020-05-03
Authors
Islam, Md Johirul
Pan, Rangeet
Nguyen, Giang
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract

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.

Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
article
Comments

This preprint is made available through arXiv: https://arxiv.org/abs/2005.00972.

Rights Statement
Copyright
Wed Jan 01 00:00:00 UTC 2020
Funding
DOI
Supplemental Resources
Source
Collections