C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
This work addresses the problem of enabling distributed machine learning in mobile, privacy-sensitive environments with spatial and temporal drift, which is critical for applications like vehicular sensing and drone monitoring.
C2FL tackles the challenge of continual federated learning under spatial and temporal drift in collective adaptive systems, where nodes must learn from privacy-sensitive, spatially clustered, and temporally evolving data. The method restores robust collective adaptation, significantly outperforming standard federated strategies that degrade under these conditions.
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.