Federated learning enables collaborative training without sharing raw data, but struggles under client heterogeneity and streaming distribution shifts, where drift and novel data can impair convergence and cause forgetting. We propose a federated associative-memory framework that learns shared archetypes in heterogeneous, continual settings, where client data are independent but not necessarily balanced. Each client encodes its experience as a low-rank Hebbian operator, sent to a central server for aggregation and factorization into global archetypes. This approach preserves privacy, avoids centralized replay buffers, and is robust to small, noisy, or evolving datasets. We cast aggregation as a low-rank-plus-noise spectral inference problem, deriving theoretical thresholds for detectability and retrieval robustness. An entropy-based controller balances stability and plasticity in streaming regimes. Experiments with heterogeneous clients, drift, and novelty show improved global archetype reconstruction and associative retrieval, supporting the spectral view of federated consolidation.

翻译：联邦学习支持在不共享原始数据的情况下进行协作训练，但在客户端异构和流式分布漂移场景下表现欠佳——漂移和新型数据会损害收敛并导致遗忘。我们提出一种联邦联想记忆框架，可在异构、持续学习环境中学习共享原型，其中各客户端数据独立但未必平衡。每个客户端将其经验编码为低秩Hebbian算子，发送至中央服务器进行聚合与分解，形成全局原型。该方法保护隐私，无需集中式回放缓冲区，且对小型、噪声或演化数据集具有鲁棒性。我们将聚合问题建模为低秩加噪声的谱推理问题，推导出可检测性与检索鲁棒性的理论阈值。基于熵的控制器可在流式场景中平衡稳定性与可塑性。针对异构客户端、漂移及新异数据的实验表明，该框架可显著提升全局原型重建与联想检索性能，为联邦记忆整合的谱视角提供实验支撑。