mlsanityData to 7 Oct 2026

Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learning

arXiv 2103.02270 ↗First posted 3 Mar 2021cs.IT cs.LG math.ITcited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate over-the-air model aggregation in a federated edge learning (FEEL) system. We introduce a Markovian probability model to characterize the intrinsic temporal structure of the model aggregation series. With this temporal probability model, we formulate the model aggregation problem as to infer the desired aggregated update given all the past observations from a Bayesian perspective. We develop a message passing based algorithm, termed temporal-structure-assisted gradient aggregation (TSA-GA), to fulfil this estimation task with low complexity and near-optimal performance. We further establish the state evolution (SE) analysis to characterize the behaviour of the proposed TSA-GA algorithm, and derive an explicit bound of the expected loss reduction of the FEEL system under certain standard regularity conditions. In addition, we develop an expectation maximization (EM) strategy to learn the unknown parameters in the Markovian model. We show that the proposed TSAGA algorithm significantly outperforms the state-of-the-art, and is able to achieve comparable learning performance as the error-free benchmark in terms of both convergence rate and final test accuracy.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

23 of 40 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  3. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  4. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  5. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  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. 2018Federated Learning via Over-the-Air Computationcited by 215
  9. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  10. 2019Federated Learning over Wireless Fading Channelscited by 178
  11. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  12. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
11 more
  1. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
  2. 2018Wireless Network Intelligence at the Edgecited by 90
  3. 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
  4. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
  5. 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
  6. 2018Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communicationcited by 51
  7. 2020Blind Federated Edge Learningcited by 42
  8. 2020Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approachcited by 32
  9. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  10. 2020Sparse Communication for Training Deep Networkscited by 10
  11. 2019Optimized Power Control for Over-the-Air Computation in Fading Channelscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 2; 2023: 5.

10 papers.

  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  2. 2023Over-the-Air Federated Learning and Optimizationcited by 10
  3. 2021Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channelscited by 7
  4. 2022Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learningcited by 7
  5. 2023Advancements in Federated Learning: Models, Methods, and Privacycited by 7
  6. 2023Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimizationcited by 7
  7. 2022CFLIT: Coexisting Federated Learning and Information Transfercited by 4
  8. 2021Over-the-Air Federated Learning with Retransmissions (Extended Version)cited by 1
  9. 2023PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learningcited by 0
  10. 2023Over-the-Air Computation Aided Federated Learning with the Aggregation of Normalized Gradientcited by 0