mlsanityData to 7 Oct 2026

Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing

arXiv 2007.09236 ↗First posted 17 Jul 2020cs.LG stat.MLcited by 52

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-federated Batch-Normalization (BN) layers into the federated DNN. MTFL benefits UA and convergence speed by allowing users to train models personalised to their own data. MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL. Experiments using MNIST and CIFAR10 demonstrate that MTFL is able to significantly reduce the number of rounds required to reach a target UA, by up to 5× when using existing FL optimisation strategies, and with a further 3× improvement when using FedAvg-Adam. We compare MTFL to competing personalised FL algorithms, showing that it is able to achieve the best UA for MNIST and CIFAR10 in all considered scenarios. Finally, we evaluate MTFL with FedAvg-Adam on an edge-computing testbed, showing that its convergence and UA benefits outweigh its overhead.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 12; 2024: 17; 2025: 12; 2026: 5.

52 papers.

Sort:

By area:

  1. 2022DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalizationcited by 35
  2. 2023Why Batch Normalization Damage Federated Learning on Non-IID Data?cited by 29
  3. 2023Intelligent Model Update Strategy for Sequential Recommendationcited by 25
  4. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  5. 2023FedICT: Federated Multi-task Distillation for Multi-access Edge Computingcited by 17
  6. 2023FedHCA2: Towards Hetero-Client Federated Multi-Task Learningcited by 17
  7. 2024Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decompositioncited by 15
  8. 2024Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computingcited by 15
  9. 2024MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysiscited by 14
  10. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  11. 2022FedDKD: Federated Learning with Decentralized Knowledge Distillationcited by 9
  12. 2023FedDWA: Personalized Federated Learning with Dynamic Weight Adjustmentcited by 9
38 more
  1. 2025dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysiscited by 8
  2. 2023Knowledge Distillation in Federated Edge Learning: A Surveycited by 5
  3. 2023BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learningcited by 5
  4. 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communicationcited by 5
  5. 2023Efficient Classification of SARS-CoV-2 Spike Sequences Using Federated Learningcited by 4
  6. 2024FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Qualitycited by 4
  7. 2024Dynamic D2D-Assisted Federated Learning over O-RAN: Performance Analysis, MAC Scheduler, and Asymmetric User Selectioncited by 3
  8. 2024DIET: Customized Slimming for Incompatible Networks in Sequential Recommendationcited by 3
  9. 2024The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learningcited by 3
  10. 2024Federated Communication-Efficient Multi-Objective Optimizationcited by 3
  11. 2025FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learningcited by 3
  12. 2022Multi-Task and Transfer Learning for Federated Learning Applicationscited by 2
  13. 2023Take Your Pick: Enabling Effective Personalized Federated Learning within Low-dimensional Feature Spacecited by 2
  14. 2024Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Studycited by 2
  15. 2024Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformationcited by 2
  16. 2025Mitigating Modality Quantity and Quality Imbalance in Multimodal Online Federated Learningcited by 2
  17. 2025Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clusteringcited by 2
  18. 2021OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learningcited by 1
  19. 2023FLAG: Fast Label-Adaptive Aggregation for Multi-label Classification in Federated Learningcited by 1
  20. 2023Elastic Federated Learning over Open Radio Access Network (O-RAN) for Concurrent Execution of Multiple Distributed Learning Taskscited by 1
  21. 2024Holistic Evaluation Metrics: Use Case Sensitive Evaluation Metrics for Federated Learningcited by 1
  22. 2024FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillationcited by 1
  23. 2024Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clientscited by 1
  24. 2024TPFL: A Trustworthy Personalized Federated Learning Framework via Subjective Logiccited by 1
  25. 2025FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworkscited by 1
  26. 2025Hierarchical Knowledge Structuring for Effective Federated Learning in Heterogeneous Environmentscited by 1
  27. 2025Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decouplingcited by 1
  28. 2022Depersonalized Federated Learning: Tackling Statistical Heterogeneity by Alternating Stochastic Gradient Descentcited by 0
  29. 2023Cross-Fusion Rule for Personalized Federated Learningcited by 0
  30. 2024Sequence-to-sequence models in peer-to-peer learning: A practical applicationcited by 0
  31. 2024Federated Learning based Latent Factorization of Tensors for Privacy-Preserving QoS Predictioncited by 0
  32. 2024SHFL: Secure Hierarchical Federated Learning Framework for Edge Networkscited by 0
  33. 2025Optimize Incompatible Parameters through Compatibility-aware Knowledge Integrationcited by 0
  34. 2025Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharingcited by 0
  35. 2025From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walkscited by 0
  36. 2026A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributionscited by 0
  37. 2026Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learningcited by 0
  38. 2026Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detectioncited by 0

50 most cited of 52 All 52 (JSON)