Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Scaling this intelligence, however, raises fundamental challenges: sensed data is often privacy-sensitive, preventing centralized collection; nodes are mobile, traversing regions where nearby nodes perceive similar phenomena while distant ones observe radically different conditions, creating natural spatial clusters; and these distributions evolve over time due to mobility, introducing temporal drift that makes local models progressively stale. These dynamics arise across domains - vehicular sensing, drone-based monitoring, smartphone crowdsensing - yet the interplay of privacy, spatial heterogeneity, and temporal drift severely undermines conventional learning strategies. Therefore, we propose C2FL, a fully distributed Federated Learning (FL) approach where nodes self-organize into learning groups through spatial clustering, reflecting the geographic structure of the environment. To counteract temporal drift, each node combines experience replay with a dwell-time-aware adaptive averaging step, progressively incorporating the regional consensus as it remains longer within the same area, while preserving previously acquired knowledge under evolving distributions. We evaluate our approach on synthetic experiments that systematically reproduce spatial and temporal shifts, showing that standard federated strategies degrade significantly under these conditions and that our method restores robust collective adaptation.

翻译：集体自适应系统（CAS）日益依赖机器学习，使每个节点能够从本地感知数据中学习，并使其行为与周围环境保持一致。然而，扩展这种智能带来了根本性挑战：感知数据通常涉及隐私敏感问题，无法集中收集；节点具有移动性，穿越不同区域时，邻近节点可感知相似现象，而远端节点则观测到截然不同的条件，从而形成自然的空间聚类；此外，由于移动性导致的这些数据分布随时间演化，引入了时间漂移，使得局部模型逐渐过时。这些动态现象出现在多个领域——车辆感知、无人机监控、智能手机众包——然而，隐私约束、空间异质性与时间漂移的相互交织严重削弱了传统学习策略的有效性。为此，我们提出C2FL，一种完全分布式的联邦学习方法，其中节点通过空间聚类自组织成学习组，以反映环境的地理结构。为应对时间漂移，每个节点将经验回放与感知停留时间的自适应平均步骤相结合，在同类区域内停留越久，逐步融入区域共识，同时在分布不断演化的情况下保持先前获得的知识。我们在系统性重现空间和时间漂移的合成实验上评估了该方法，结果表明标准联邦策略在这些条件下性能显著下降，而我们的方法则恢复了鲁棒的集体自适应能力。