CAPL: Graph Few-Shot Class-Incremental Learning Via Class-Adaptive Prototype Learning
Lists
Only you see this
Abstract
Few-shot class-incremental learning has always been a challenging problem due to catastrophic forgetting, insufficient labels and class imbalance. Graph few-shot class-incremental learning(GFSCIL), with the presence of edges between nodes and complex relationships between classes, further increases the difficulty of the learning process. Current researches in this field mainly employ meta-learning and metric-learning approaches. However, these methods do not consider the relation- ships between classes and treat all classes equally, which does not conform to the real-world applications. To address these limitations, we propose a class-adaptive prototype learning (CAPL) method that adaptively processes each class based on the relationships between classes, thereby alleviating spatial confusion between new and old classes as well as the catastrophic forgetting problem. Specifically, we first adopt a class-adaptive spatial reservation module to allocate larger spaces for the arrival of new classes, preventing confusion between new and old classes. We then utilize a class-adaptive prototype alignment module for knowledge distil- lation. By considering the positional relationship between new and old classes in the feature space, we provide greater flexibility to classes closely related to new classes while retaining classification information of old classes, thus adapting to the arrival of new classes. Experiment results demonstrate the superiority of the proposed method.
BibTeX
@misc{zhang2026capl,
author = {Qin Zhang and Weixing Lin and Luowei Fan and Han Liu and Huisi Wu},
title = {{CAPL: Graph Few-Shot Class-Incremental Learning Via Class-Adaptive Prototype Learning}},
year = {2026},
url = {https://openreview.net/forum?id=B6t4qcdmM0},
howpublished = {OpenReview},
note = {Submitted to ICLR 2026},
}