Continual Learning under Open-World Distribution Shift

This review examines continual learning under open-world distribution shift. The organizing question is how adaptive models can acquire new knowledge while preserving prior capability and detecting unsupported novelty. Ten related scholarly sources are synthesized through a decision-centered framework spanning problem definition, mechanism, measurement, evaluation, implementation, and governance. The review does not invent experiments, pooled estimates, or unreported quantitative results. It instead evaluates the strength and transferability of the available evidence, with particular attention to measuring average retention without testing safety-critical forgetting. The resulting framework links technical or empirical performance to explicit use conditions and identifies tests that should precede wider adoption in long-lived intelligent systems.

1. Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2021). A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7), 1. https://doi.org/10.1109/tpami.2021.3057446 DOI
2. Hadsell, R., Rao, D., Rusu, A. A., & Pascanu, R. (2020). Embracing Change: Continual Learning in Deep Neural Networks. Trends in Cognitive Sciences, 24(12), 1028-1040. https://doi.org/10.1016/j.tics.2020.09.004 DOI
3. Lesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., & Díaz-Rodríguez, N. (2019). Continual Learning for Robotics: Definition, Framework, Learning\n Strategies, Opportunities and Challenges. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1907.00182 DOI
4. Lopez-Paz, D., & Ranzato, M. A. (2017). Gradient Episodic Memory for Continual Learning. arXiv (Cornell University), 30, 6467-6476. https://doi.org/10.48550/arxiv.1706.08840 DOI
5. Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., & Sanner, S. (2021). Online continual learning in image classification: An empirical survey. Neurocomputing, 469, 28-51. https://doi.org/10.1016/j.neucom.2021.10.021 DOI
6. Nguyen, C. V., Li, Y., Bui, T. D., & Turner, R. E. (2017). Variational Continual Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1710.10628 DOI
7. Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019). Continual lifelong learning with neural networks: A review. Neural Networks, 113, 54-71. https://doi.org/10.1016/j.neunet.2019.01.012 DOI
8. Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T. P., & Wayne, G. (2018). Experience Replay for Continual Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1811.11682 DOI
9. van de Ven, G. M., & Tolias, A. S. (2019). Three scenarios for continual learning. Lirias. https://doi.org/10.48550/arxiv.1904.07734 DOI
10. Wang, L., Zhang, X., Su, H., & Zhu, J. (2024). A Comprehensive Survey of Continual Learning: Theory, Method and Application. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8), 5362-5383. https://doi.org/10.1109/tpami.2024.3367329 DOI