mlsanityData to 14 Oct 2026

Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels

arXiv 2112.13603 ↗First posted 27 Dec 2021eess.SP cs.LG cs.NIcited by 8

Not on the map. Why?

Abstract (arXiv)

With the explosive growth of data and wireless devices, federated learning (FL) over wireless medium has emerged as a promising technology for large-scale distributed intelligent systems. Yet, the urgent demand for ubiquitous intelligence will generate a large number of concurrent FL tasks, which may seriously aggravate the scarcity of communication resources. By exploiting the analog superposition of electromagnetic waves, over-the-air computation (AirComp) is an appealing solution to alleviate the burden of communication required by FL. However, sharing frequency-time resources in over-the-air computation inevitably brings about the problem of inter-task interference, which poses a new challenge that needs to be appropriately addressed. In this paper, we study over-the-air federated multi-task learning (OA-FMTL) over the multiple-input multiple-output (MIMO) multiple access (MAC) channel. We propose a novel model aggregation method for the alignment of local gradients of different devices, which alleviates the straggler problem in over-the-air computation due to the channel heterogeneity. We establish a communication-learning analysis framework for the proposed OA-FMTL scheme by considering the spatial correlation between devices, and formulate an optimization problem for the design of transceiver beamforming and device selection. To solve this problem, we develop an algorithm by using alternating optimization (AO) and fractional programming (FP), which effectively mitigates the impact of inter-task interference on the FL learning performance. We show that due to the use of the new model aggregation method, device selection is no longer essential, thereby avoiding the heavy computational burden involved in selecting active devices. Numerical results demonstrate the validity of the analysis and the superb performance of the proposed scheme.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 27 Dec 2021.

Builds on

22 of 41 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  5. 2018Deep Learning for Classical Japanese Literaturecited by 422
  6. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
  7. 2018Federated Learning via Over-the-Air Computationcited by 219
  8. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  9. 2019Federated Learning over Wireless Fading Channelscited by 183
  10. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  11. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
  12. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
10 more
  1. 2018Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamformingcited by 46
  2. 2020Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computingcited by 39
  3. 2020Federated Learning for 6G Communications: Challenges, Methods, and Future Directionscited by 33
  4. 2020Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approachcited by 33
  5. 2019Cell-Free Massive MIMO for Wireless Federated Learningcited by 25
  6. 2021ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Trainingcited by 22
  7. 2021Over-the-Air Decentralized Federated Learningcited by 18
  8. 2021Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learningcited by 10
  9. 2021Wireless Federated Learning (WFL) for 6G Networks -- Part II: The Compute-then-Transmit NOMA Paradigmcited by 6
  10. 2021CSIT-Free Model Aggregation for Federated Edge Learning via Reconfigurable Intelligent Surfacecited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 0; 2025: 2.

8 papers.

  1. 2022A Survey on Over-the-Air Computationcited by 21
  2. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  3. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  4. 2023Digital Over-the-Air Federated Learning in Multi-Antenna Systemscited by 1
  5. 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 0
  6. 2023Over-the-Air Computation in OFDM Systems with Imperfect Channel State Informationcited by 0
  7. 2025Quantized Analog Beamforming Enabled Multi-task Federated Learning Over-the-aircited by 0
  8. 2025From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learning
  2. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
  3. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
  4. 2025Optimal Transceiver Design in Over-the-Air Federated Distillation
  5. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
  6. 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling
  7. 2022Over-the-Air Federated Learning via Second-Order Optimization
  8. 2024Adaptive Federated Learning Over the Air