FedGTEA通过高斯任务嵌入实现高效联邦增量学习，缓解遗忘且保护隐私。
FedGTEA: Federated Class-Incremental Learning with Gaussian Task Embedding and Alignment
- 客户端用固定参数的编码器生成高斯任务嵌入，适应多任务场景。
- 服务器用2-Wasserstein距离度量任务差异，减少遗忘，准确率优于基线。
- 无需传输原始嵌入，保障任务级隐私，适合长期增量学习场景。
我们提出一种新型联邦类增量学习框架FedGTEA，旨在以可扩展且通信高效的方式捕捉任务特定知识并建模不确定性。客户端采用无基数依赖的任务编码器（CATE），生成高斯分布的任务嵌入，编码任务知识、缓解统计异质性并量化数据不确定性。重要的是，CATE的参数量不随任务数量增加，支持长序列任务的可扩展性。服务端利用2-Wasserstein距离衡量高斯嵌入间的任务间隔，通过构建Wasserstein损失强制任务间分离。该概率化形式不仅增强表征学习，还避免直接传输潜在嵌入，符合联邦学习的隐私约束。在多个主流数据集上的大量实验表明，FedGTEA在分类性能上显著优于现有强基线，并有效缓解遗忘问题。
原文摘要 · Abstract (English)
We introduce a novel framework for Federated Class Incremental Learning, called Federated Gaussian Task Embedding and Alignment (FedGTEA). FedGTEA is designed to capture task-specific knowledge and model uncertainty in a scalable and communication-efficient manner. At the client side, the Cardinality-Agnostic Task Encoder (CATE) produces Gaussian-distributed task embeddings that encode task knowledge, address statistical heterogeneity, and quantify data uncertainty. Importantly, CATE maintains a fixed parameter size regardless of the number of tasks, which ensures scalability across long task sequences. On the server side, FedGTEA utilizes the 2-Wasserstein distance to measure inter-task gaps between Gaussian embeddings. We formulate the Wasserstein loss to enforce inter-task separation. This probabilistic formulation not only enhances representation learning but also preserves task-level privacy by avoiding the direct transmission of latent embeddings, aligning with the privacy constraints in federated learning. Extensive empirical evaluations on popular datasets demonstrate that FedGTEA achieves superior classification performance and significantly mitigates forgetting, consistently outperforming strong existing baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。