This is the implementation code of the CVPR 2022 paper "Federated Class-Incremental Learning". You can also find the arXiv version with supplementary materials here. More related works are provided at Dynamic Federated Learning, please work with us to make FL more practical and realistic.

2023年6月20日 · 为了满足 fcil 的要求，本文模型通过类别意识梯度补偿损失和类别语义关系蒸馏损失来解决本地遗忘问题，同时通过代理服务器为本地客户端选择最佳旧模型来解决全局遗忘问题。

2024年1月1日 · In response to this challenge, we propose a novel Federated Class-Incremental Learning (FCIL) method, named \underline {Fed}erated \underline {C}lass-Incremental \underline {L}earning with New-Class \underline {A}ugmented \underline {S}elf …

This is the implementation code of the CVPR 2022 paper "Federated Class-Incremental Learning". You can also find the arXiv version with supplementary materials here. More related works are provided at Dynamic Federated Learning, please work with us to make FL more practical and realistic.

First, FCIL-MSN achieves collaborative onboard model updates by introducing FCIL into MSNs. Second, a bias calibration-guided relationship distillation module constructs a pseudo-feature set by collaborative MSNs, which alleviates the model bias caused by class imbalance from a global perspective, thereby enhancing model performance.

2025年3月24日 · In this paper, we propose the Weighted Aggregation and Distillation-based FCIL (WAD-FCIL) method to address these limitations. To address data heterogeneity arising from class imbalance, we first introduce a task-aware client clustering method to identify clients with extreme class deviations before global model aggregation to eliminate ...

2023年10月13日 · In this paper, we propose a novel method called Federated Class-Incremental Learning with PrompTing (FCILPT). Given the privacy and limited memory, FCILPT does not use a rehearsal-based buffer to keep exemplars of old data. We choose to use prompts to ease the catastrophic forgetting of the old classes.

2023年8月1日 · fcil的目标是通过与全局中央服务器 s g s_g s g 通信本地模型参数，有效地训练全局模型参数，连续学习新类，同时在隐私保护的要求下缓解对旧类的灾难性遗忘。

To address these challenges, we develop a novel Global-Local Forgetting Compensation (GLFC) model, to learn a global class incremental model for alleviating the catastrophic forgetting from both local and global perspectives.

2024年1月10日 · FCIL是Foreign, Comparative, and International Law的常用缩写，涵盖了外国法、比较法和国际法的翻译。 由于涉及法律术语和制度差异，这种翻译需依赖熟悉多国法律和国际法律体系的专家。