Bugs in machine learning-based systems: a faultload benchmark

Abstract

Rapid growth of applying Machine Learning (ML) in different domains, especially in safety-critical areas, increases the need for reliable ML components, i.e., a software component operating based on ML. Since corrective maintenance, i.e. identifying and resolving systems bugs, is a key task in the software development process to deliver reliable software components, it is necessary to investigate the usage of ML components, from the software maintenance perspective. Understanding the bugs characteristics and maintenance challenges in ML-based systems can help developers of these systems to identify where to focus maintenance and testing efforts, by giving insights into the most error-prone components, most common bugs, etc. In this paper, we investigate the characteristics of bugs in ML-based software systems and the difference between ML and non-ML bugs from the maintenance viewpoint. We extracted 447,948 GitHub repositories that used one of the three most popular ML frameworks, i.e., TensorFlow, Keras, and PyTorch. After multiple filtering steps, we select the top 300 repositories with the highest number of closed issues. We manually investigate the extracted repositories to exclude non-MLbased systems. Our investigation involved a manual inspection of 386 sampled reported issues in the identified ML-based systems to indicate whether they affect ML components or not. Our analysis shows that nearly half of the real