mlsanityData to 14 Oct 2026

Tighter Regret Analysis and Optimization of Online Federated Learning

arXiv 2205.06491 ↗First posted 13 May 2022cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

In federated learning (FL), it is commonly assumed that all data are placed at clients in the beginning of machine learning (ML) optimization (i.e., offline learning). However, in many real-world applications, it is expected to proceed in an online fashion. To this end, online FL (OFL) has been introduced, which aims at learning a sequence of global models from decentralized streaming data such that the so-called cumulative regret is minimized. Combining online gradient descent and model averaging, in this framework, FedOGD is constructed as the counterpart of FedSGD in FL. While it can enjoy an optimal sublinear regret, FedOGD suffers from heavy communication costs. In this paper, we present a communication-efficient method (named OFedIQ) by means of intermittent transmission (enabled by client subsampling and periodic transmission) and quantization. For the first time, we derive the regret bound that captures the impact of data-heterogeneity and the communication-efficient techniques. Through this, we efficiently optimize the parameters of OFedIQ such as sampling rate, transmission period, and quantization levels. Also, it is proved that the optimized OFedIQ can asymptotically achieve the performance of FedOGD while reducing the communication costs by 99%. Via experiments with real datasets, we demonstrate the effectiveness of the optimized OFedIQ.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 13 May 2022.

Builds on

22 of 42 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  6. 2019Introduction to Online Convex Optimizationcited by 803
  7. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  8. 2019Federated Machine Learning: Concept and Applicationscited by 412
  9. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  10. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  11. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  12. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 107
10 more
  1. 2021Federated Learning: Opportunities and Challengescited by 84
  2. 2019Variance Reduced Local SGD with Lower Communication Complexitycited by 80
  3. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 36
  4. 2017Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamicscited by 28
  5. 2021UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approachcited by 20
  6. 2021Communication-Efficient Online Federated Learning Framework for Nonlinear Regressioncited by 16
  7. 2020Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Methodcited by 9
  8. 2021Distributed Online Learning with Multiple Kernelscited by 9
  9. 2022FedVQCS: Federated Learning via Vector Quantized Compressed Sensingcited by 9
  10. 2020Active Learning with Multiple Kernelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 6; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Online Vertical Federated Learning for Cooperative Spectrum Sensingcited by 6
  2. 2024On the Necessity of Collaboration for Online Model Selection with Decentralized Datacited by 6
  3. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  4. 2023Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricingcited by 2
  5. 2025Multimodal Online Federated Learning with Modality Missing in Internet of Thingscited by 2
  6. 2025Mitigating Modality Quantity and Quality Imbalance in Multimodal Online Federated Learningcited by 2
  7. 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
  8. 2025Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learningcited by 1
  9. 2025Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentumcited by 0
  10. 2025Event-Driven Online Vertical Federated Learningcited by 0
  11. 2025Federated Reinforcement Learning in Heterogeneous Environmentscited by 0
  12. 2026FedSEA: Achieving Benefit of Parallelization in Federated Online Learningcited by 0
2 more
  1. 2026OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularizationcited by 0
  2. 2026Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Federated Offline Policy Learning
  2. 2024Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents
  3. 2022Communication-Efficient Federated Learning With Data and Client Heterogeneity
  4. 2024Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
  5. 2023Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling
  6. 2026FedSGM: A Unified Framework for Constraint Aware, Bidirectionally Compressed, Multi-Step Federated Optimization
  7. 2026Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
  8. 2025Decentralized Federated Averaging via Random Walk