C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

• URL: http://arxiv.org/abs/2606.18003v1
• Date: Tue, 16 Jun 2026 14:50:20 GMT
• Title: C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
• Abstract summary: We propose a fully distributed Federated Learning (FL) approach where nodes self-organize into learning groups through spatial clustering.<n>We evaluate our approach on synthetic experiments that systematically reproduce spatial and temporal shifts.
• Score: 1.6332363167294173
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data [0.16206783799607727]
  We propose a novel Causal Adrial Subspace Clusteringgeneration (CASC) framework for discovering latent regimes in high-dimensional data.<n>CASC integrates a U-Net-inspired deep adversarial clustering architecture with stacked FAConvLSTM layers to preserve spatial and temporal structure.<n>We also propose two new learning objectives: (1) a Causal Preservation Loss that aligns self-expression with latent causal relationships, and (2) a Dynamic Temporal Subspace Evolution Loss that captures evolving subspace structures and temporal regime transitions in nonstationary environments.
  arXiv  Detail & Related papers  (2026-07-23T09:19:17Z)
• Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning [83.67663266193308]
  Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge.<n>In real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments.<n>We propose a unified framework to address domain shift and catastrophic forgetting simultaneously.
  arXiv  Detail & Related papers  (2026-05-09T09:49:13Z)
• Autonomous Drift Learning in Data Streams: A Unified Perspective [21.166882700131293]
  In pursuit of autonomous learning systems, the premise that data distributions and model behaviors remain constant, is fundamentally untenable.<n>We propose a novel, three-dimensional taxonomy that systematizes the field based on the operational state of the system.<n>By bridging the fragmented paradigms of drift adaptation, continual learning, and temporal generalization, this survey outlines a roadmap for building self-evolving intelligent systems.
  arXiv  Detail & Related papers  (2026-05-02T07:11:38Z)
• Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training [46.01525213637453]
  We introduce PBT-NCA, a meta-evolutionary algorithm that evolves a population of Petri Dish Neural Cellular Automata.<n>By actively penalizing monocultures and dead states, PBT-NCA sustains a state of effective complexity that is neither globally ordered nor globally random.
  arXiv  Detail & Related papers  (2026-04-13T09:56:22Z)
• Attention-Guided Deep Adversarial Temporal Subspace Clustering (A-DATSC) Model for multivariate spatiotemporal data [0.16206783799607727]
  Subspace clustering models are vital for applications such as snowmelt detection sea ice tracking.<n>A graph attention based self-expressive network captures local spatial relationships, global dependencies, and both short- and long-range preserves.<n> Experiments on three real-world datasets show that A-SCSC achieves substantially superior clustering performance compared to state-of-the-art deep subspace clustering models.
  arXiv  Detail & Related papers  (2025-10-20T18:38:26Z)
• RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion [64.49056527678606]
  We propose a Token-wise Attention integrated into not only the U-Net diffusion model but also the radar-temporal encoder.<n>Unlike prior approaches, our method integrates attention into the architecture without incurring the high resource cost typical of pixel-space diffusion.<n>Our experiments and evaluations demonstrate that the proposed method significantly outperforms state-of-the-art approaches, robustness local fidelity, generalization, and superior in complex precipitation forecasting scenarios.
  arXiv  Detail & Related papers  (2025-10-16T17:59:13Z)
• Accelerating Privacy-Preserving Federated Learning in Large-Scale LEO Satellite Systems [57.692181589325116]
  Large-scale low-Earth-orbit (LEO) satellite systems are increasingly valued for their ability to enable rapid and wide-area data exchange.<n>Due to privacy concerns and regulatory constraints, raw data collected at remote clients cannot be centrally aggregated.<n>Federated learning offers a privacy-preserving alternative by training local models on distributed devices and exchanging only model parameters.<n>We propose a discrete temporal graph-based on-demand scheduling framework that dynamically allocates communication resources to accelerate federated learning.
  arXiv  Detail & Related papers  (2025-09-05T03:33:42Z)
• Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics [65.72663487116439]
  We propose nTPP-GMM that models spawn-temporal spawn dynamics using Neural Temporal Point Processes.<n>We evaluate our approach by simulations of three diverse real-world datasets with nTPP-GMM.
  arXiv  Detail & Related papers  (2025-03-20T18:46:41Z)
• HSTFL: A Heterogeneous Federated Learning Framework for Misaligned Spatiotemporal Forecasting [6.00534246138727]
  We propose a Heterogeneous Spatiotemporal Learning (HSTFL) framework to enable multiple clients to harness time series data from different domains. We show that HSTFL not only effectively resists inference attacks but also provides a significant improvement against various baselines.
  arXiv  Detail & Related papers  (2024-09-27T06:51:11Z)
• FedASTA: Federated adaptive spatial-temporal attention for traffic flow prediction [30.346763969306398]
  Mobile devices and the Internet of Things (IoT) devices nowadays generate a large amount of heterogeneous spatial-temporal data. It remains a challenging problem to model the spatial-temporal dynamics under privacy concern. We propose a novel Federated Adaptive spatial-temporal Attention (FedASTA) framework to model the dynamic spatial-temporal relations.
  arXiv  Detail & Related papers  (2024-05-21T11:44:07Z)
• Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting [47.1051445072085]
  We argue to rethink the sensor's dependency modeling from two hierarchies: regional and global. We generate representative and common-temporal patterns as global nodes to reflect a global dependency between sensors. In pursuit of the generality of reality of node representations, we incorporate a Meta GCN to propagate and global nodes in the physical data space.
  arXiv  Detail & Related papers  (2023-09-20T13:08:34Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• Multi-Temporal Relationship Inference in Urban Areas [75.86026742632528]
  Finding temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. We propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation learning and further handle the relationship sparsity.
  arXiv  Detail & Related papers  (2023-06-15T07:48:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.