Class Incremental Learning from First Principles: A Review
Abstract
Continual learning systems attempt to efficiently learn over time without forgetting previously acquired knowledge. In recent years, there has been an explosion of work on continual learning, mainly focused on the class-incremental learning (CIL) setting. In this review, we take a step back and reconsider the CIL problem. We reexamine the problem definition and describe its unique challenges, contextualize existing solutions by analyzing non-continual approaches, and investigate the implications of various problem configurations. Our goal is to provide an alternative perspective to existing work on CIL and direct attention toward unexplored aspects of the problem.
Cite
Text
Ashtekar et al. "Class Incremental Learning from First Principles: A Review." Transactions on Machine Learning Research, 2025.Markdown
[Ashtekar et al. "Class Incremental Learning from First Principles: A Review." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/ashtekar2025tmlr-class/)BibTeX
@article{ashtekar2025tmlr-class,
title = {{Class Incremental Learning from First Principles: A Review}},
author = {Ashtekar, Neil and Zhu, Jingxi and Honavar, Vasant G},
journal = {Transactions on Machine Learning Research},
year = {2025},
url = {https://mlanthology.org/tmlr/2025/ashtekar2025tmlr-class/}
}