Federated Class-Incremental Learning (FCIL) focuses on continually
transferring the previous knowledge to learn new classes in dynamic Federated
Learning (FL). However, existing methods do not consider the trustworthiness of
FCIL, i.e., improving continual utility, privacy, and efficiency
simultaneously, which is greatly influenced by catastrophic forgetting and data
heterogeneity among clients. To address this issue, we propose FedProK
(Federated Prototypical Feature Knowledge Transfer), leveraging prototypical
feature as a novel representation of knowledge to perform spatial-temporal
knowledge transfer. Specifically, FedProK consists of two components: (1)
feature translation procedure on the client side by temporal knowledge transfer
from the learned classes and (2) prototypical knowledge fusion on the server
side by spatial knowledge transfer among clients. Extensive experiments
conducted in both synchronous and asynchronous settings demonstrate that our
FedProK outperforms the other state-of-the-art methods in three perspectives of
trustworthiness, validating its effectiveness in selectively transferring
spatial-temporal knowledge.

Federated Class-Incremental Learning (FCIL) aims to improve trustworthiness by transferring knowledge using FedProK, a method that leverages prototypical feature knowledge transfer, demonstrating superior performance in spatial-temporal knowledge transfer.

FedProK: 基于样本原型特征知识迁移的可信联邦增量学习

FedProK: Trustworthy Federated Class-Incremental Learning via  Prototypical Feature Knowledge Transfer

Federated Class-Incremental Learning (FCIL) is an underexplored yet pivotal
issue, involving the dynamic addition of new classes in the context of
federated learning. In this field, Data-Free Knowledge Transfer (DFKT) plays a
crucial role in addressing catastrophic forgetting and data privacy problems.
However, prior approaches lack the crucial synergy between DFKT and the model
training phases, causing DFKT to encounter difficulties in generating
high-quality data from a non-anchored latent space of the old task model. In
this paper, we introduce LANDER (Label Text Centered Data-Free Knowledge
Transfer) to address this issue by utilizing label text embeddings (LTE)
produced by pretrained language models. Specifically, during the model training
phase, our approach treats LTE as anchor points and constrains the feature
embeddings of corresponding training samples around them, enriching the
surrounding area with more meaningful information. In the DFKT phase, by using
these LTE anchors, LANDER can synthesize more meaningful samples, thereby
effectively addressing the forgetting problem. Additionally, instead of tightly
constraining embeddings toward the anchor, the Bounding Loss is introduced to
encourage sample embeddings to remain flexible within a defined radius. This
approach preserves the natural differences in sample embeddings and mitigates
the embedding overlap caused by heterogeneous federated settings. Extensive
experiments conducted on CIFAR100, Tiny-ImageNet, and ImageNet demonstrate that
LANDER significantly outperforms previous methods and achieves state-of-the-art
performance in FCIL. The code is available at
this https URL

利用预训练语言模型生成的标签文本嵌入（LTE），通过在模型训练阶段将样本嵌入约束在这些锚点周围，丰富了周围区域的有意义信息，从而更好地解决了遗忘问题。同时，引入了边界损失以保留样本嵌入的灵活性，减少异构联邦环境中的嵌入重叠，使得 LANDER 在 FCIL 中表现出色。

文本增强的无数据联邦类增量学习方法

Text-Enhanced Data-free Approach for Federated Class-Incremental  Learning

Federated Learning (FL) enables collaborative model training among
participants while guaranteeing the privacy of raw data. Mainstream FL
methodologies overlook the dynamic nature of real-world data, particularly its
tendency to grow in volume and diversify in classes over time. This oversight
results in FL methods suffering from catastrophic forgetting, where models
inadvertently discard previously learned information upon assimilating new
data. In response to this challenge, we propose a novel Federated
Class-Incremental Learning (FCIL) method, named FCIL with New-Class Augmented
Self-Distillation (FedNASD). FedNASD combines new class scores, which are
inferred from current models, with historical models' predictions. Based on the
combined past and present knowledge, it incorporates self-distillation over
models on clients, aiming to achieve effective knowledge transfer from
historical models to current models. Theoretical analysis demonstrates that
FedNASD is equivalent to modeling old class scores as conditional probabilities
in the absence of new classes. Additionally, it reconciles the predictions of
new classes with current models to refine the conditional probabilities of
historical scores where new classes do not exist. Empirical experiments
demonstrate the superiority of FedNASD over four baseline algorithms in
reducing the average forgetting rate and boosting global accuracy.

我们提出了一种新颖的联邦类增量学习方法（FCIL），命名为具有新类增强的自我蒸馏（FedNASD）。FedNASD 通过将当前模型推断的新类分数与历史模型的预测相结合，基于过去和现在的知识，它在客户端上进行自我蒸馏，旨在实现从历史模型到当前模型的有效知识转移。理论分析表明，在没有新类的情况下，FedNASD 等效地对旧类分数建模为条件概率。此外，它通过将新类的预测与当前模型相结合，以修正历史得分的条件概率，在不存在新类的情况下。经验实验表明，FedNASD 在降低平均遗忘率和提高全局准确性方面优于其他四种基准算法。