mlsanityData to 7 Oct 2026

DoCoFL: Downlink Compression for Cross-Device Federated Learning

arXiv 2302.00543 ↗First posted 1 Feb 2023cs.LG cs.AI stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

Many compression techniques have been proposed to reduce the communication overhead of Federated Learning training procedures. However, these are typically designed for compressing model updates, which are expected to decay throughout training. As a result, such methods are inapplicable to downlink (i.e., from the parameter server to clients) compression in the cross-device setting, where heterogeneous clients textitmay appear only once during training and thus must download the model parameters. Accordingly, we propose textsfDoCoFL -- a new framework for downlink compression in the cross-device setting. Importantly, textsfDoCoFL can be seamlessly combined with many uplink compression schemes, rendering it suitable for bi-directional compression. Through extensive evaluation, we show that textsfDoCoFL offers significant bi-directional bandwidth reduction while achieving competitive accuracy to that of a baseline without any compression.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 44 of its 67 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

44 of 67 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2020Adaptive Federated Optimizationcited by 1,036
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  8. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  9. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  10. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 361
  11. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 306
  12. 2017TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learningcited by 253
32 more
  1. 2019PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimizationcited by 234
  2. 2018The Convergence of Sparsified Gradient Methodscited by 228
  3. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  4. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 159
  5. 2020Better Theory for SGD in the Nonconvex Worldcited by 156
  6. 2020On Biased Compression for Distributed Learningcited by 140
  7. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  8. 2021EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedbackcited by 131
  9. 2015Asynchronous Parallel Stochastic Gradient for Nonconvex Optimizationcited by 115
  10. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  11. 2015Convolutional neural networks with low-rank regularizationcited by 102
  12. 2019DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compressioncited by 98
  13. 2019Natural Compression for Distributed Deep Learningcited by 88
  14. 2019Communication-efficient distributed SGD with Sketchingcited by 81
  15. 2021MARINA: Faster Non-Convex Distributed Learning with Compressioncited by 77
  16. 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 53
  17. 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
  18. 2019Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedbackcited by 49
  19. 2018A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updatescited by 47
  20. 2020Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressorcited by 45
  21. 2020Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guaranteescited by 45
  22. 2020A Better Alternative to Error Feedback for Communication-Efficient Distributed Learningcited by 42
  23. 2016Randomized Distributed Mean Estimation: Accuracy vs Communicationcited by 39
  24. 2020Stochastic-Sign SGD for Federated Learning with Theoretical Guaranteescited by 34
  25. 2021Asynchronous Stochastic Optimization Robust to Arbitrary Delayscited by 32
  26. 2019A Double Residual Compression Algorithm for Efficient Distributed Learningcited by 31
  27. 2022EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compressioncited by 28
  28. 2021Preserved central model for faster bidirectional compression in distributed settingscited by 21
  29. 2019NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantizationcited by 17
  30. 2019At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?cited by 16
  31. 2019Distributed Fixed Point Methods with Compressed Iteratescited by 11
  32. 2021Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketchingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 10; 2026: 6.

27 papers.

Sort:

By area:

  1. 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
  2. 2023Momentum Provably Improves Error Feedback!cited by 31
  3. 2023THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compressioncited by 15
  4. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  5. 2024LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compressioncited by 11
  6. 2024FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusioncited by 11
  7. 2024Ferret: Federated Full-Parameter Tuning at Scale for Large Language Modelscited by 6
  8. 2025Mitigating Unintended Memorization with LoRA in Federated Learning for LLMscited by 6
  9. 2024Blockchain-empowered Federated Learning: Benefits, Challenges, and Solutionscited by 5
  10. 2025The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learningcited by 5
  11. 2026DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reducecited by 4
  12. 2026Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Provencited by 4
15 more
  1. 2025Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practicecited by 3
  2. 2024Optimal and Near-Optimal Adaptive Vector Quantizationcited by 2
  3. 2024Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradientscited by 2
  4. 2024Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learningcited by 2
  5. 2025FedFetch: Faster Federated Learning with Adaptive Downstream Prefetchingcited by 2
  6. 2025γ-FedHT: Stepsize-Aware Hard-Threshold Gradient Compression in Federated Learningcited by 1
  7. 2025Tight analyses of first-order methods with error feedbackcited by 1
  8. 2025On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approachcited by 1
  9. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezingcited by 1
  10. 2025H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learningcited by 1
  11. 2025Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learningcited by 0
  12. 2026Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guaranteecited by 0
  13. 2026From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learningcited by 0
  14. 2026DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accountingcited by 0
  15. 2026TORQUE: Optimizing What (not) to Quantize Before and After Rotationcited by 0