mlsanityData to 14 Oct 2026

SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks

arXiv 2203.14094 ↗First posted 26 Mar 2022cs.LG cs.AI cs.NAcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a key enabler for efficient communication and computing, leveraging devices' distributed computing capabilities. However, applying FL in practice is challenging due to the local devices' heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions. To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN). Integrating FL with SNNs is challenging due to time-varying channel conditions and data distributions. In addition, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, which makes SNN ill-suited for FL. Motivated by this, we propose a communication and energy-efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST) for updating local models. By applying SC, SlimFL exchanges the superposition of multiple-width configurations decoded as many times as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations while avoiding inter-width interference during backpropagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also deals with non-IID data distributions and poor channel conditions, which is also corroborated by data-intensive simulations.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 26 Mar 2022.

Builds on

28 of 61 references.

References · 28

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  8. 2020Adaptive Federated Optimizationcited by 1,046
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  10. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  11. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  12. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
16 more
  1. 2020Federated Learning with Matched Averagingcited by 564
  2. 2021A Field Guide to Federated Optimizationcited by 315
  3. 2018Slimmable Neural Networkscited by 305
  4. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  5. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
  6. 2019Universally Slimmable Networks and Improved Training Techniquescited by 221
  7. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  8. 2019Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocationcited by 94
  9. 2021Dynamic Slimmable Networkcited by 83
  10. 2020Measuring the Algorithmic Efficiency of Neural Networkscited by 52
  11. 2021Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systemscited by 45
  12. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  13. 2020Dynamic Sparsity Neural Networks for Automatic Speech Recognitioncited by 23
  14. 2020Communication-Efficient Multimodal Split Learning for mmWave Received Power Predictioncited by 18
  15. 2021Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networkscited by 14
  16. 20206G Wireless Channel Measurements and Models: Trends and Challengescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 4; 2025: 0; 2026: 1.

6 papers.

  1. 2022Slimmable Quantum Federated Learningcited by 23
  2. 2024SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overheadcited by 9
  3. 2024Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Clientcited by 0
  4. 2024Federated Learning with Multi-resolution Model Broadcastcited by 0
  5. 2024Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offscited by 0
  6. 2026HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding
  2. 2022CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
  3. 2023Communication-Efficient Federated Learning via Regularized Sparse Random Networks
  4. 2024FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models
  5. 2021Communication-Efficient Federated Learning with Binary Neural Networks
  6. 2025Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing
  7. 2026CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
  8. 2022Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices