On the Value of Oversampling for Deep Learning in Software Defect Prediction
This work addresses software defect prediction for developers and researchers, offering an incremental improvement by optimizing preprocessing steps to enhance deep learning performance.
The paper tackled the problem of deep learning for software defect prediction by showing that automatic feature engineering does not excuse manual preprocessing, and demonstrated that a novel oversampling technique called fuzzy sampling within the GHOST pipeline outperforms prior state-of-the-art deep learning methods in 14 out of 20 datasets, achieving faster training.
One truism of deep learning is that the automatic feature engineering (seen in the first layers of those networks) excuses data scientists from performing tedious manual feature engineering prior to running DL. For the specific case of deep learning for defect prediction, we show that that truism is false. Specifically, when we preprocess data with a novel oversampling technique called fuzzy sampling, as part of a larger pipeline called GHOST (Goal-oriented Hyper-parameter Optimization for Scalable Training), then we can do significantly better than the prior DL state of the art in 14/20 defect data sets. Our approach yields state-of-the-art results significantly faster deep learners. These results present a cogent case for the use of oversampling prior to applying deep learning on software defect prediction datasets.