# C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

arXiv: https://arxiv.org/abs/2606.18003 · HTML: https://mlsanity.com/paper/2606.18003/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Recent Advances on Federated Learning: A Systematic Survey](https://mlsanity.com/paper/2301.01299/) (2023)
- [Non-IID data and Continual Learning processes in Federated Learning: A long road ahead](https://mlsanity.com/paper/2111.13394/) (2021)
- [Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks](https://mlsanity.com/paper/2108.09103/) (2021)
- [Concept drift detection and adaptation for federated and continual learning](https://mlsanity.com/paper/2105.13309/) (2021)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks](https://mlsanity.com/paper/2401.09656/) (2024)
- [Federated Continual Learning for Edge-AI: A Comprehensive Survey](https://mlsanity.com/paper/2411.13740/) (2024)
- [Class-Incremental Learning with Repetition](https://mlsanity.com/paper/2301.11396/) (2023)
- [Towards Lifelong Federated Learning in Autonomous Mobile Robots with Continuous Sim-to-Real Transfer](https://mlsanity.com/paper/2205.15496/) (2022)
- [Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data](https://mlsanity.com/paper/2402.00205/) (2024)
- [FBFL: A Field-Based Coordination Approach for Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2502.08577/) (2025)
- [ProFed: a Benchmark for Proximity-based non-IID Federated Learning](https://mlsanity.com/paper/2503.20618/) (2025)
- [Attentive Federated Learning for Concept Drift in Distributed 5G Edge Networks](https://mlsanity.com/paper/2111.07457/) (2021)
- [Geographical Node Clustering and Grouping to Guarantee Data IIDness in Federated Learning](https://mlsanity.com/paper/2410.15693/) (2024)
- [Phyelds: A Pythonic Framework for Aggregate Computing](https://mlsanity.com/paper/2603.29999/) (2026)

## Built on by (most cited first, 1 of 1)

- [Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning](https://mlsanity.com/paper/2606.30499/) (2026)

## Abstract (arXiv)

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.