mlsanityData to 7 Oct 2026

Efficient Wireless Federated Learning with Partial Model Aggregation

arXiv 2204.09746 ↗First posted 20 Apr 2022cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The data heterogeneity across devices and the limited communication resources, e.g., bandwidth and energy, are two of the main bottlenecks for wireless federated learning (FL). To tackle these challenges, we first devise a novel FL framework with partial model aggregation (PMA). This approach aggregates the lower layers of neural networks, responsible for feature extraction, at the parameter server while keeping the upper layers, responsible for complex pattern recognition, at devices for personalization. The proposed PMA-FL is able to address the data heterogeneity and reduce the transmitted information in wireless channels. Then, we derive a convergence bound of the framework under a non-convex loss function setting to reveal the role of unbalanced data size in the learning performance. On this basis, we maximize the scheduled data size to minimize the global loss function through jointly optimize the device scheduling, bandwidth allocation, computation and communication time division policies with the assistance of Lyapunov optimization. Our analysis reveals that the optimal time division is achieved when the communication and computation parts of PMA-FL have the same power. We also develop a bisection method to solve the optimal bandwidth allocation policy and use the set expansion algorithm to address the device scheduling policy. Compared with the benchmark schemes, the proposed PMA-FL improves 3.13% and 11.8% accuracy on two typical datasets with heterogeneous data distribution settings, i.e., MINIST and CIFAR-10, respectively. In addition, the proposed joint dynamic device scheduling and resource management approach achieve slightly higher accuracy than the considered benchmarks, but they provide a satisfactory energy and time reduction: 29% energy or 20% time reduction on the MNIST; and 25% energy or 12.5% time reduction on the CIFAR-10.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 23 of its 50 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

23 of 50 references.

References · 23

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2021Convex optimizationcited by 2,479
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  7. 2019Federated Learning with Personalization Layerscited by 533
  8. 2021Towards Personalized Federated Learningcited by 462
  9. 2020Adaptive Personalized Federated Learningcited by 353
  10. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  11. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  12. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
11 more
  1. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  2. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 138
  3. 2022Federated Learning with Partial Model Personalizationcited by 114
  4. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  5. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  6. 2020Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computingcited by 39
  7. 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 34
  8. 2020Federated Learning and Wireless Communicationscited by 27
  9. 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
  10. 2021Efficient Federated Meta-Learning over Multi-Access Wireless Networkscited by 13
  11. 2021Robust Federated Learning via Over-The-Air Computationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 2.

8 papers.

  1. 2023Deep Model Fusion: A Surveycited by 89
  2. 2024Latency Minimization for UAV-Enabled Federated Learning: Trajectory Design and Resource Allocationcited by 3
  3. 2024Online-Score-Aided Federated Learning for Resource-Constrained Wireless Clients with Continual Data Arrivalcited by 1
  4. 2025FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clientscited by 1
  5. 2025Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharingcited by 0
  6. 2025UltraFlwr -- An Efficient Federated Surgical Object Detection Frameworkcited by 0
  7. 2026Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networkscited by 0
  8. 2026A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraintscited by 0