mlsanityData to 14 Oct 2026

Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning

arXiv 1910.10453 ↗First posted 23 Oct 2019cs.LG cs.DC cs.ITcited by 17

Not on the map. Why?

Abstract (arXiv)

In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direction method of multipliers (GADMM). Moreover, each worker transmits the quantized difference between its current model and its previously quantized model, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the spatial sparsity and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex and stochastic problems, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic sampling. Simulation results corroborate that Q-GADMM significantly outperforms GADMM in terms of communication efficiency while achieving the same accuracy and convergence speed for a linear regression task. Similarly, for an image classification task using DNN, Q-SGADMM achieves significantly less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 3; 2024: 5; 2025: 2.

17 papers.

Sort:

By area:

  1. 2022FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learningcited by 23
  2. 2023Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updatescited by 21
  3. 2024Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysiscited by 21
  4. 2022Wireless Quantized Federated Learning: A Joint Computation and Communication Designcited by 15
  5. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  6. 2022Distributed Learning With Sparsified Gradient Differencescited by 9
  7. 2024Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Methodcited by 4
  8. 2024Distributed Learning based on 1-Bit Gradient Coding in the Presence of Stragglerscited by 4
  9. 2021Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffscited by 3
  10. 2024Rate-Constrained Quantization for Communication-Efficient Federated Learningcited by 3
  11. 2022Scaling up Stochastic Gradient Descent for Non-convex Optimisationcited by 1
  12. 2024Communication and Energy Efficient Federated Learning using Zero-Order Optimization Techniquecited by 1
5 more
  1. 2025Communication-Efficient Zero-Order and First-Order Federated Learning Methods over Wireless Networkscited by 1
  2. 2025Decentralized Optimization with Topology-Independent Communicationcited by 1
  3. 2021Generalized ADMM in Distributed Learning via Variational Inequalitycited by 0
  4. 2023Federated Learning for Energy Constrained IoT devices: A systematic mapping studycited by 0
  5. 2023Distributed Linear Regression with Compositional Covariatescited by 0