cs.CVNov 11, 2026

Federated Class Incremental Learning: A Pseudo Feature Based Approach Without Exemplars

Authors: Min Kyoon Yoo, Yu Rang Park

Organizations: Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea

Abstract

Federated learning often assumes that data is fixed in advance, which is unrealistic in many real-world scenarios where new data continuously arrives, causing catastrophic forgetting. To address this challenge, we propose FCLPF (Federated Class Incremental Learning with Pseudo Features), a method that uses pseudo features generated from prototypes to mitigate catastrophic forgetting. Our approach reduces communication costs and improves efficiency by eliminating the need for past data and avoiding computationally heavy models like GANs. Experimental results on CIFAR-100 show that FCLPF achieves an average accuracy of 51.87% and an average forgetting of 9.62%, significantly outperforming existing baselines with an average accuracy of 47.72% and forgetting of 20.46%. On TinyImageNet, FCLPF achieves 37.56% accuracy and 3.14% forgetting, compared to the baselines' 27.69% accuracy and 24.46% forgetting, demonstrating the superior performance of FCLPF.

Figures & tables

Explore similar work

CardsList
  1. Federated Class-Incremental Learning with Hierarchical Generative Prototypes

    Jun 4, 2024Riccardo Salami, Pietro Buzzega, Matteo Mosconi +2Class-Incremental LearningPrototype-Based Classification

  2. Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning

    Jun 27, 2026Wenhao Yuan, Chenchen Lin, Jian Chen +3Class-Incremental LearningFederated Continual Learning

  3. Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning

    Feb 19, 2026Obaidullah Zaland, Zulfiqar Ahmad Khan, Monowar BhuyanFederated LearningFederated Continual Learning