Reproduce, Replicate, Reevaluate. The Long but Safe Way to Extend Machine Learning Methods
DOI:
https://doi.org/10.1609/aaai.v38i14.29515Keywords:
ML: Transparent, Interpretable, Explainable ML, ML: Applications, ML: Ethics, Bias, and Fairness, ML: Graph-based Machine Learning, ML: Neuro-Symbolic Learning, ML: Representation LearningAbstract
Reproducibility is a desirable property of scientific research. On the one hand, it increases confidence in results. On the other hand, reproducible results can be extended on a solid basis. In rapidly developing fields such as machine learning, the latter is particularly important to ensure the reliability of research. In this paper, we present a systematic approach to reproducing (using the available implementation), replicating (using an alternative implementation) and reevaluating (using different datasets) state-of-the-art experiments. This approach enables the early detection and correction of deficiencies and thus the development of more robust and transparent machine learning methods. We detail the independent reproduction, replication, and reevaluation of the initially published experiments with a method that we want to extend. For each step, we identify issues and draw lessons learned. We further discuss solutions that have proven effective in overcoming the encountered problems. This work can serve as a guide for further reproducibility studies and generally improve reproducibility in machine learning.Downloads
Published
2024-03-24
How to Cite
Werner, L., Layaïda, N., Genevès, P., Euzenat, J., & Graux, D. (2024). Reproduce, Replicate, Reevaluate. The Long but Safe Way to Extend Machine Learning Methods. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15850-15858. https://doi.org/10.1609/aaai.v38i14.29515
Issue
Section
AAAI Technical Track on Machine Learning V