联邦学习各客户端标签不同步？PRO用投影记忆代替生成回放，不用额外预训练，在异构环境下表现更稳，值得做增量学习的试试。
论文提出PRO框架，用投影排练编排替代合成输入回放，在服务器维护紧凑的类级投影记忆。客户端通过平衡伪多任务训练结合当前样本和旧投影记忆。进一步提出的PRO-MAX增加了邻域加权记忆对齐。在图像、文本、图基准上，PRO和PRO-MAX在异构流下提升了保留率和最终效用，而基线即便扩大回放预算仍因监督不平衡退化，证明回放数量不足以解决质量问题。
When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning
Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at different stages, and provide uneven supervision for the same semantic concepts. Existing FCIL methods often preserve old knowledge through input-space synthesis, but they can be fragile under heterogeneous task streams and difficult to transfer across modalities. To alleviate such issues, we propose PRO, a framework that replaces synthetic input replay with projected rehearsal orchestration. To remove external pretraining, we evaluate all methods under the same warmup. After this, PRO maintains compact class-level projected memories on the server and allows clients perform balanced pseudo multi-task training over current examples and old projected memories. To handle stronger representation drift, we further introduce PRO-MAX, which augments PRO with neighborhood-weighted memory alignment while preserving the same server-light principle that the server only aggregates model updates and memory statistics. Across image, text, and graph benchmarks, PRO and PRO-MAX improve retention and final utility under heterogeneous streams while remaining competitive in homogeneous FCIL. Even when baselines are given expanded replay budgets, they degrade under supervision imbalance and stage misalignment, indicating that replay quantity alone does not resolve replay-quality failures. Additional weak-task diagnostics further show that larger replay mismatch is associated with larger downstream degradation, while our method keeps projected memories better aligned with the evolving representation.