mlsanityData to 14 Oct 2026

Federated Continual Learning for Edge-AI: A Comprehensive Survey

arXiv 2411.13740 ↗First posted 20 Nov 2024cs.LG cs.AI cs.DCcited by 11

Not on the map. Why?

Abstract (arXiv)

Edge-AI, the convergence of edge computing and artificial intelligence (AI), has become a promising paradigm that enables the deployment of advanced AI models at the network edge, close to users. In Edge-AI, federated continual learning (FCL) has emerged as an imperative framework, which fuses knowledge from different clients while preserving data privacy and retaining knowledge from previous tasks as it learns new ones. By so doing, FCL aims to ensure stable and reliable performance of learning models in dynamic and distributed environments. In this survey, we thoroughly review the state-of-the-art research and present the first comprehensive survey of FCL for Edge-AI. We categorize FCL methods based on three task characteristics: federated class continual learning, federated domain continual learning, and federated task continual learning. For each category, an in-depth investigation and review of the representative methods are provided, covering background, challenges, problem formalisation, solutions, and limitations. Besides, existing real-world applications empowered by FCL are reviewed, indicating the current progress and potential of FCL in diverse application domains. Furthermore, we discuss and highlight several prospective research directions of FCL such as algorithm-hardware co-design for FCL and FCL with foundation models, which could provide insights into the future development and practical deployment of FCL in the era of Edge-AI.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 170 references that are in the map. First posted on arXiv 20 Nov 2024.

Builds on

24 of 170 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  4. 2023SLoRA: Federated Parameter Efficient Fine-Tuning of Language Modelscited by 93
  5. 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
  6. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  7. 2021A distillation-based approach integrating continual learning and federated learning for pervasive servicescited by 42
  8. 2023pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuningcited by 40
  9. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  10. 2023Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learningcited by 21
  11. 2023FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clientscited by 19
  12. 2022Continual Learning for Peer-to-Peer Federated Learning: A Study on Automated Brain Metastasis Identificationcited by 13
12 more
  1. 2021Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsalcited by 11
  2. 2022Federated Continual Learning for Text Classification via Selective Inter-client Transfercited by 9
  3. 2023Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learningcited by 9
  4. 2023FedYolo: Augmenting Federated Learning with Pretrained Transformerscited by 9
  5. 2020FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learningcited by 6
  6. 2023Continual Adaptation of Vision Transformers for Federated Learningcited by 6
  7. 2023Federated Class-Incremental Learning with Promptingcited by 5
  8. 2022Federated Continual Learning to Detect Accounting Anomalies in Financial Auditingcited by 4
  9. 2023A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutionscited by 3
  10. 2020Federated and continual learning for classification tasks in a society of devicescited by 2
  11. 2023Failure-Sentient Composition For Swarm-Based Drone Servicescited by 2
  12. 2023Masked Autoencoders are Efficient Continual Federated Learnerscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 3.

11 papers.

  1. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  2. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  3. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  4. 2025Resource-Constrained Federated Continual Learning: What Does Matter?cited by 5
  5. 2025Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuningcited by 1
  6. 2025FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learningcited by 1
  7. 2026C2FL: Clustered Continual Federated Learning under Spatial and Temporal Driftcited by 1
  8. 2025Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learningcited by 0
  9. 2025Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learningcited by 0
  10. 2026PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Taskscited by 0
  11. 2026When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Datacited by 0