mlsanityData to 7 Oct 2026

Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis

arXiv 2101.12704 ↗First posted 29 Jan 2021cs.IT cs.LG cs.NIcited by 51

Not on the map. Why?

Abstract (arXiv)

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 29 Jan 2021.

Builds on

38 of 52 references.

References · 38

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  5. 2018Sparsified SGD with Memorycited by 373
  6. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  7. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  8. 2019Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computingcited by 225
  9. 2019Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communicationcited by 218
  10. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  11. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 179
  12. 2019Federated Learning over Wireless Fading Channelscited by 178
26 more
  1. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  2. 2018D2: Decentralized Training over Decentralized Datacited by 140
  3. 2017Network Topology and Communication-Computation Tradeoffs in Decentralized Optimizationcited by 119
  4. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
  5. 2019Decentralized Deep Learning with Arbitrary Communication Compressioncited by 109
  6. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
  7. 2019Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networkscited by 79
  8. 2018Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimizationcited by 76
  9. 2019MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Samplingcited by 67
  10. 2020Wireless Communications for Collaborative Federated Learningcited by 47
  11. 2019Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Datacited by 39
  12. 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
  13. 2020PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learningcited by 35
  14. 2020Decentralized Federated Learning via SGD over Wireless D2D Networkscited by 32
  15. 2019Over-the-Air Computation Systems: Optimization, Analysis and Scaling Lawscited by 25
  16. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  17. 2020Decentralized SGD with Over-the-Air Computationcited by 16
  18. 2020Decentralized optimization over noisy, rate-constrained networks: Achieving consensus by communicating differencescited by 12
  19. 2016Over-the-air Function Computation in Sensor Networkscited by 11
  20. 2021Federated Learning over Noisy Channels: Convergence Analysis and Design Examplescited by 8
  21. 2019SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Stochastic Optimizationcited by 3
  22. 2015Graph colouring algorithmscited by 2
  23. 2020Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyondcited by 2
  24. 2019An introduction to decentralized stochastic optimization with gradient trackingcited by 1
  25. 2019On a Decentralized (Delta+1)-Graph Coloring Algorithmcited by 1
  26. 2021BE-RAN: Blockchain-enabled Open RAN for 6G with DID and Privacy-Preserving Communicationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 14; 2024: 9; 2025: 10; 2026: 7.

51 papers.

Sort:

By area:

  1. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  2. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  3. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  4. 2022An Energy and Carbon Footprint Analysis of Distributed and Federated Learningcited by 16
  5. 2022Asynchronous Decentralized Learning over Unreliable Wireless Networkscited by 13
  6. 2022Communication-Efficient Distributionally Robust Decentralized Learningcited by 10
  7. 2023Over-the-Air Federated Learning and Optimizationcited by 10
  8. 2025Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Frameworkcited by 10
  9. 2022Non-Coherent Over-the-Air Decentralized Gradient Descentcited by 9
  10. 2023Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Predictioncited by 9
  11. 2021Bayesian Variational Federated Learning and Unlearning in Decentralized Networkscited by 8
  12. 2023Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMIcited by 6
38 more
  1. 2024Decentralized Federated Learning Over Imperfect Communication Channelscited by 5
  2. 2024DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networkscited by 5
  3. 2023Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregationcited by 4
  4. 2023Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AIcited by 4
  5. 2025Biased Federated Learning under Wireless Heterogeneitycited by 4
  6. 2023Decentralized Learning over Wireless Networks: The Effect of Broadcast with Random Accesscited by 3
  7. 2023Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applicationscited by 3
  8. 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
  9. 2023Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clippingcited by 2
  10. 2023Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Samplingcited by 2
  11. 2023Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channelscited by 2
  12. 2024How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learningcited by 2
  13. 2024Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networkscited by 2
  14. 2024Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approachcited by 2
  15. 2022UAV-Aided Decentralized Learning over Mesh Networkscited by 1
  16. 2022UAV-Aided Multi-Community Federated Learningcited by 1
  17. 2022Over-The-Air Clustered Wireless Federated Learningcited by 1
  18. 2023Digital Over-the-Air Federated Learning in Multi-Antenna Systemscited by 1
  19. 2023Scheduling and Communication Schemes for Decentralized Federated Learningcited by 1
  20. 2024Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Designcited by 1
  21. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-offcited by 1
  22. 2025Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learningcited by 1
  23. 2026Decentralized Federated Learning With Energy Harvesting Devicescited by 1
  24. 2022FLAGS Framework for Comparative Analysis of Federated Learning Algorithmscited by 0
  25. 2023Over-the-Air Computation Aided Federated Learning with the Aggregation of Normalized Gradientcited by 0
  26. 2024Efficient Wireless Federated Learning via Low-Rank Gradient Factorizationcited by 0
  27. 2024Compressed Bayesian Federated Learning for Reliable Passive Radio Sensing in Industrial IoTcited by 0
  28. 2025Enhancing Federated Learning Through Secure Cluster-Weighted Client Aggregationcited by 0
  29. 2025Communication Optimization for Decentralized Learning atop Bandwidth-limited Edge Networkscited by 0
  30. 2025Scaling Decentralized Learning with FLockcited by 0
  31. 2025SGFusion: Stochastic Geographic Gradient Fusion in Federated Learningcited by 0
  32. 2025DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learningcited by 0
  33. 2025Timely Parameter Updating in Over-the-Air Federated Learningcited by 0
  34. 2026Hybrid Federated Learning for Noise-Robust Trainingcited by 0
  35. 2026Interference-Robust Non-Coherent Over-the-Air Computation for Decentralized Optimizationcited by 0
  36. 2026Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networkscited by 0
  37. 2026Decentralized Gradient Descent: Bottleneck Regimes and Budget Complexitycited by 0
  38. 2026Mixed-Timescale Differential Coding for Downlink Model Broadcast in Wireless Federated Learningcited by 0

50 most cited of 51 All 51 (JSON)