mlsanityData to 14 Oct 2026

Asynchronous Federated Continual Learning

arXiv 2304.03626 ↗First posted 7 Apr 2023cs.LG cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

The standard class-incremental continual learning setting assumes a set of tasks seen one after the other in a fixed and predefined order. This is not very realistic in federated learning environments where each client works independently in an asynchronous manner getting data for the different tasks in time-frames and orders totally uncorrelated with the other ones. We introduce a novel federated learning setting (AFCL) where the continual learning of multiple tasks happens at each client with different orderings and in asynchronous time slots. We tackle this novel task using prototype-based learning, a representation loss, fractal pre-training, and a modified aggregation policy. Our approach, called FedSpace, effectively tackles this task as shown by the results on the CIFAR-100 dataset using 3 different federated splits with 50, 100, and 500 clients, respectively. The code and federated splits are available at https://github.com/LTTM/FedSpace.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

27 of 38 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  6. 2017Continual Learning with Deep Generative Replaycited by 1,158
  7. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  8. 2021Model-Contrastive Federated Learningcited by 766
  9. 2019Large Scale Incremental Learningcited by 732
  10. 2018End-to-End Incremental Learningcited by 597
  11. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  12. 2019Asynchronous Federated Optimizationcited by 267
15 more
  1. 2021Co2L: Contrastive Continual Learningcited by 244
  2. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  3. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 132
  4. 2022Federated Class-Incremental Learningcited by 127
  5. 2021Pre-training without Natural Imagescited by 100
  6. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  7. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  8. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  9. 2022On the Importance and Applicability of Pre-Training for Federated Learningcited by 71
  10. 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
  11. 2021Federated Multi-Target Domain Adaptationcited by 44
  12. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  13. 2020Continual Local Training for Better Initialization of Federated Modelscited by 34
  14. 2021Improving Fractal Pre-trainingcited by 26
  15. 2021Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learningcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 8; 2026: 9.

29 papers.

Sort:

By area:

  1. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  2. 2024PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learningcited by 19
  3. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  4. 2023Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learningcited by 12
  5. 2025Federated Continual Instruction Tuningcited by 12
  6. 2024Continual Learning for Smart City: A Surveycited by 9
  7. 2024FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfercited by 9
  8. 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgettingcited by 9
  9. 2025EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inferencecited by 9
  10. 2024Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyondcited by 5
  11. 2024FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweightingcited by 5
  12. 2024When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weathercited by 4
17 more
  1. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  2. 2025Federated-Continual Dynamic Segmentation of Histopathology guided by Barlow Continuitycited by 2
  3. 2025C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learningcited by 2
  4. 2025Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learningcited by 2
  5. 2024Feature Aggregation with Latent Generative Replay for Federated Continual Learning of Socially Appropriate Robot Behaviourscited by 1
  6. 2024FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learningcited by 1
  7. 2023Distributed Continual Learning with CoCoA in High-dimensional Linear Regressioncited by 0
  8. 2025Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCLcited by 0
  9. 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalancecited by 0
  10. 2026FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocationcited by 0
  11. 2026From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneitycited by 0
  12. 2026Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Studycited by 0
  13. 2026PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Taskscited by 0
  14. 2026When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learningcited by 0
  15. 2026Robust Federated Learning Under Real-World Client Churncited by 0
  16. 2026HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learningcited by 0
  17. 2026Federated Continual Learning as a Distributed Drift-Plus-Penalty Control Problemcited by 0