mlsanityData to 7 Oct 2026

Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference

arXiv 2305.05933 ↗First posted 10 May 2023cs.LG cs.CR cs.ITcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a widely embraced paradigm for distilling artificial intelligence from distributed mobile data. However, the deployment of FL in mobile networks can be compromised by exposure to interference from neighboring cells or jammers. Existing interference mitigation techniques require multi-cell cooperation or at least interference channel state information, which is expensive in practice. On the other hand, power control that treats interference as noise may not be effective due to limited power budgets, and also that this mechanism can trigger countermeasures by interference sources. As a practical approach for protecting FL against interference, we propose Spectrum Breathing, which cascades stochastic-gradient pruning and spread spectrum to suppress interference without bandwidth expansion. The cost is higher learning latency by exploiting the graceful degradation of learning speed due to pruning. We synchronize the two operations such that their levels are controlled by the same parameter, Breathing Depth. To optimally control the parameter, we develop a martingale-based approach to convergence analysis of Over-the-Air FL with spectrum breathing, termed AirBreathing FL. We show a performance tradeoff between gradient-pruning and interference-induced error as regulated by the breathing depth. Given receive SIR and model size, the optimization of the tradeoff yields two schemes for controlling the breathing depth that can be either fixed or adaptive to channels and the learning process. As shown by experiments, in scenarios where traditional Over-the-Air FL fails to converge in the presence of strong interference, AirBreahing FL with either fixed or adaptive breathing depth can ensure convergence where the adaptive scheme achieves close-to-ideal performance.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 10 May 2023.

Builds on

24 of 48 references.

References · 24

  1. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  2. 2018Sparsified SGD with Memorycited by 373
  3. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  4. 2018The Convergence of Sparsified Gradient Methodscited by 228
  5. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
  6. 2018Federated Learning via Over-the-Air Computationcited by 215
  7. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  8. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  9. 2019Federated Learning over Wireless Fading Channelscited by 178
  10. 2019The Roadmap to 6G -- AI Empowered Wireless Networkscited by 150
  11. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  12. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
12 more
  1. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  2. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
  3. 2021Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devicescited by 56
  4. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  5. 2020Federated Learning via Intelligent Reflecting Surfacecited by 38
  6. 2015Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithmscited by 31
  7. 2021Time-Correlated Sparsification for Communication-Efficient Federated Learningcited by 25
  8. 2021Federated Learning over Energy Harvesting Wireless Networkscited by 17
  9. 2020Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learningcited by 15
  10. 2021Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysiscited by 13
  11. 2021BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackerscited by 6
  12. 2020Simultaneous Signal-and-Interference Alignment for Two-Cell Over-the-Air Computationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 2.

9 papers.

  1. 2025Revisiting Outage for Edge Inference Systemscited by 5
  2. 2026SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networkscited by 3
  3. 2024FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networkscited by 2
  4. 2025Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneitycited by 2
  5. 2025FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuningcited by 2
  6. 2024Unified Error Correction Code Transformer with Low Complexitycited by 1
  7. 2024LoLaFL: Low-Latency Federated Learning via Forward-only Propagationcited by 1
  8. 2025Generative Feature Imputing -- A Technique for Error-resilient Semantic Communicationcited by 1
  9. 2026Efficient Resource Optimization for Split Federated Learningcited by 0