Replay-Based Continual Learning for Test Case Prioritization - A Fariha, Dr A Azim, Dr R Liscano

This talk discusses integrating pre-training and replay-based continual learning methods to enhance test case prioritization. Pre-training-based continual learning leverages the strong representation by pre-training models on a large dataset. This approach helps initialize the model with a broad understanding, which can be further incrementally trained to accommodate new tasks without significant performance loss on previous tasks. The dataset we got from IBM has a few years of test execution data for CI and VCS. The model can be trained on a large volume of data for the pre-training method. Replay-based continual learning, on the other hand, involves retaining a small buffer of old training samples. This strategy includes a small fraction of old samples with a new dataset while incrementally training the model, enabling it to maintain its performance on older tasks by reinforcing previous learnings. Integrating pre-training and replay-based methods was found to be most effective in the literature.

Pre-training provides a solid foundation of generic knowledge; replay-based methods complement this by continuously reinforcing past learnings, ensuring that the adaptation to new tasks does not come at the expense of previously acquired knowledge.
Presented by Asma Fariha, Dr Akramul Azim, and Dr Ramiro Liscano of Ontario Tech University at the CI/CD Industry Workshop at ICST 2024, the 17th IEEE International Conference on Software Testing, Verification and Validation

Видео Replay-Based Continual Learning for Test Case Prioritization - A Fariha, Dr A Azim, Dr R Liscano канала CI-CD Industry Workshop, ICST