Self-Supervised Bug Detection and Repair
arXiv:2105.12787
Abstract
Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development. However, in the absence of large annotated corpora, training these analyses is challenging. Towards addressing this, we present BugLab, an approach for self-supervised learning of bug detection and repair. BugLab co-trains two models: (1) a detector model that learns to detect and repair bugs in code, (2) a selector model that learns to create buggy code for the detector to use as training data. A Python implementation of BugLab improves by up to 30% upon baseline methods on a test dataset of 2374 real-life bugs and finds 19 previously unknown bugs in open-source software.
arXiv commentPublished in NeurIPS 2021
References in corpus (7)
- Neural Message Passing for Quantum Chemistry
- Learning and Evaluating Contextual Embedding of Source Code
- ReZero is All You Need: Fast Convergence at Large Depth
- Semantic Robustness of Models of Source Code
- LambdaNet: Probabilistic Type Inference using Graph Neural Networks
- Neural Program Repair by Jointly Learning to Localize and Repair
- How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Dataset