DeepLocalize: Fault Localization for Deep Neural Networks

Deep Neural Networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques don't support localizing DNN bugs because of the lack of understanding of model behaviors. The entire DNN model appears a...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Software Engineering pp. 251 - 262
Main Authors: Wardat, Mohammad, Le, Wei, Rajan, Hridesh
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2021
Subjects:
Benchmark testing
Computer bugs
Debugging
Deep learning bugs
Deep Neural Networks
Fault diagnosis
Fault Location
Neural networks
Numerical models
Program Analysis
ISBN:1665402962, 9781665402965
ISSN:1558-1225
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep Neural Networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques don't support localizing DNN bugs because of the lack of understanding of model behaviors. The entire DNN model appears as a black box. To address these problems, we propose an approach and a tool that automatically determines whether the model is buggy or not, and identifies the root causes for DNN errors. Our key insight is that historic trends in values propagated between layers can be analyzed to identify faults, and also localize faults. To that end, we first enable dynamic analysis of deep learning applications: by converting it into an imperative representation and alternatively using a callback mechanism. Both mechanisms allows us to insert probes that enable dynamic analysis over the traces produced by the DNN while it is being trained on the training data. We then conduct dynamic analysis over the traces to identify the faulty layer or hyperparameter that causes the error. We propose an algorithm for identifying root causes by capturing any numerical error and monitoring the model during training and finding the relevance of every layer/parameter on the DNN outcome. We have collected a benchmark containing 40 buggy models and patches that contain real errors in deep learning applications from Stack Overflow and GitHub. Our benchmark can be used to evaluate automated debugging tools and repair techniques. We have evaluated our approach using this DNN bug-and-patch benchmark, and the results showed that our approach is much more effective than the existing debugging approach used in the state-of-the-practice Keras library. For 34/40 cases, our approach was able to detect faults whereas the best debugging approach provided by Keras detected 32/40 faults. Our approach was able to localize 21/40 bugs whereas Keras did not localize any faults.
ISBN:1665402962
9781665402965
ISSN:1558-1225
DOI:10.1109/ICSE43902.2021.00034