LCA: Local Classifier Alignment for Continual Learning

ICLR 2026 Conference Submission16828 Authors

Keywords: continual Learning, local robustness, catastrophic forgetting

TL;DR: A novel local robustness loss to align classifiers after integrating backbones in continual learning.

Abstract: A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently emerged as a promising solution, since their generalized feature extractors enable faster and more robust adaptation. While some earlier works mitigate forgetting by fine-tuning only on the first task, this approach quickly deteriorates as the number of tasks grows and the data distributions diverge. More recent research instead seeks to consolidate task knowledge into a unified backbone, or adapting the backbone as new tasks arrive. However, such approaches may create a (potential) $\textit{mismatch}$ between task-specific classifiers and the adapted backbone. To address this issue, we propose a novel $\textit{Local Classifier Alignment}$ (LCA) loss to better align the classifier with backbone. Theoretically, we show that this LCA loss can enable the classifier to not only generalize well for all observed tasks, but also improve robustness. Furthermore, we develop a complete solution for continual learning, following the model merging approach and using LCA. Extensive experiments on several standard benchmarks demonstrate that our method often achieves leading performance, sometimes surpasses the state-of-the-art methods with a large margin.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 16828