Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning

• URL: http://arxiv.org/abs/2512.24069v1
• Date: Tue, 30 Dec 2025 08:24:28 GMT
• Title: Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning
• Abstract summary: We propose a theoretically-justified solution for mixing matrix design that aims at minimizing the maximum per-node energy consumption until convergence.<n>Our evaluations based on real data have validated the efficacy of the proposed solution in combining the low energy consumption of sparse mixing matrices and the fast convergence of dense mixing matrices.
• Score: 6.831984901330601
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the design of mixing matrices to minimize the operation cost for decentralized federated learning (DFL) in wireless networks, with focus on minimizing the maximum per-node energy consumption. As a critical hyperparameter for DFL, the mixing matrix controls both the convergence rate and the needs of agent-to-agent communications, and has thus been studied extensively. However, existing designs mostly focused on minimizing the communication time, leaving open the minimization of per-node energy consumption that is critical for energy-constrained devices. This work addresses this gap through a theoretically-justified solution for mixing matrix design that aims at minimizing the maximum per-node energy consumption until convergence, while taking into account the broadcast nature of wireless communications. Based on a novel convergence theorem that allows arbitrarily time-varying mixing matrices, we propose a multi-phase design framework that activates time-varying communication topologies under optimized budgets to trade off the per-iteration energy consumption and the convergence rate while balancing the energy consumption across nodes. Our evaluations based on real data have validated the efficacy of the proposed solution in combining the low energy consumption of sparse mixing matrices and the fast convergence of dense mixing matrices.

Related papers

• Optimizing Stochastic Gradient Push under Broadcast Communications [5.019739507685787]
  We consider the problem of minimizing the convergence time for decentralized federated learning (DFL) in wireless networks under broadcast communications.<n>We focus on mixing matrix design, which simultaneously controls the convergence rate across iterations and the communication demand per iteration.<n>Our evaluations show that the proposed solution can notably reduce the convergence time compared to the state of the art without compromising the quality of the trained model.
  arXiv  Detail & Related papers  (2026-04-16T21:56:57Z)
• A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning [0.0]
  Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices.<n>We propose Cost-Weighted Magnitude Pruning (CWMP), a selection rule that prioritizes parameter updates based on their magnitude relative to their physical cost.<n> Numerical results on a non-IIDAR-10 benchmark show that CWMP consistently establishes a superior performance-energy frontier compared to the Top-K baseline.
  arXiv  Detail & Related papers  (2026-03-23T18:31:07Z)
• Lightweight Federated Learning over Wireless Edge Networks [83.4818741890634]
  Federated (FL) is an alternative at network edge, but an alternative in wireless networks.<n>We derive a closed-form expression FL convergence gap transmission power, model pruning error, and quantization.<n> LTFL outperforms state-the-art schemes in experiments on real-world datasets.
  arXiv  Detail & Related papers  (2025-07-13T09:14:17Z)
• Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding [4.8310710966636545]
  In this paper, we investigate the compute energy efficiency of mMIMO precoders using deep learning approaches.<n>We propose a framework that incorporates mixed-precision quantization-aware training and neural architecture search to reduce energy usage.<n>Our results show that deep neural network compression generates precoders with up to 35 times higher energy efficiency than WMMSE at equal performance.
  arXiv  Detail & Related papers  (2025-02-12T20:03:32Z)
• AoI in Context-Aware Hybrid Radio-Optical IoT Networks [8.467370216900107]
  We study hybrid IoT networks that employ Optical Communication (OC) as a reinforcement medium to Radio Frequency (RF)<n>We adopt a multi-objective optimization strategy to balance the collection of the throughput with the minimization of energy and the frequency of switching between technologies.<n> Simulation results show that the OC supplementary integration alongside enhances the network's overall performances and significantly reduces the Mean AoI and Peak AoI.
  arXiv  Detail & Related papers  (2024-12-17T13:48:25Z)
• Federated Learning With Energy Harvesting Devices: An MDP Framework [17.87295300394514]
  Federated learning (FL) requires that edge devices conduct local training and communicate with a parameter server, resulting in significant energy consumption.<n>A key challenge in practical FL systems is the rapid depletion of battery-limited edge devices, which limits their operational lifespan and impacts learning performance.<n>We implement energy harvesting techniques in FL systems to capture ambient energy, thereby providing continuous power to edge devices.
  arXiv  Detail & Related papers  (2024-05-17T03:41:40Z)
• Adaptive Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks [4.03161352925235]
  In Federated Learning (FL), with parameter aggregated by a central node, the communication overhead is a substantial concern. Recent studies have introduced Decentralized Federated Learning (DFL) as a viable alternative. We formulate a problem that minimizes the loss function of DFL while considering energy and latency constraints.
  arXiv  Detail & Related papers  (2024-03-29T09:17:40Z)
• Multiagent Reinforcement Learning with an Attention Mechanism for Improving Energy Efficiency in LoRa Networks [52.96907334080273]
  As the network scale increases, the energy efficiency of LoRa networks decreases sharply due to severe packet collisions. We propose a transmission parameter allocation algorithm based on multiagent reinforcement learning (MALoRa) Simulation results demonstrate that MALoRa significantly improves the system EE compared with baseline algorithms.
  arXiv  Detail & Related papers  (2023-09-16T11:37:23Z)
• Federated Learning for Energy-limited Wireless Networks: A Partial Model Aggregation Approach [79.59560136273917]
  limited communication resources, bandwidth and energy, and data heterogeneity across devices are main bottlenecks for federated learning (FL) We first devise a novel FL framework with partial model aggregation (PMA) The proposed PMA-FL improves 2.72% and 11.6% accuracy on two typical heterogeneous datasets.
  arXiv  Detail & Related papers  (2022-04-20T19:09:52Z)
• Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning [63.83425382922157]
  Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
  arXiv  Detail & Related papers  (2022-03-26T20:37:14Z)
• Efficient Federated Meta-Learning over Multi-Access Wireless Networks [26.513076310183273]
  Federated meta-learning (FML) has emerged as a promising paradigm to cope with the data limitation and heterogeneity challenges in today's edge learning arena. This paper develops an FML algorithm (called NUFM) with a non-uniform device selection scheme to accelerate the convergence. We propose a resource allocation problem integrating NUFM in multi-access wireless systems to jointly improve the convergence rate and minimize the wall-clock time along with energy cost.
  arXiv  Detail & Related papers  (2021-08-14T03:23:04Z)
• Threshold-Based Data Exclusion Approach for Energy-Efficient Federated Edge Learning [4.25234252803357]
  Federated edge learning (FEEL) is a promising distributed learning technique for next-generation wireless networks. FEEL might significantly shorten energy-constrained participating devices' lifetime due to the power consumed during the model training round. This paper proposes a novel approach that endeavors to minimize computation and communication energy consumption during FEEL rounds.
  arXiv  Detail & Related papers  (2021-03-30T13:34:40Z)
• Risk-Aware Energy Scheduling for Edge Computing with Microgrid: A Multi-Agent Deep Reinforcement Learning Approach [82.6692222294594]
  We study a risk-aware energy scheduling problem for a microgrid-powered MEC network. We derive the solution by applying a multi-agent deep reinforcement learning (MADRL)-based advantage actor-critic (A3C) algorithm with shared neural networks.
  arXiv  Detail & Related papers  (2020-02-21T02:14:38Z)
• Targeted free energy estimation via learned mappings [66.20146549150475]
  Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences. FEP suffers from a severe limitation: the requirement of sufficient overlap between distributions. One strategy to mitigate this problem, called Targeted Free Energy Perturbation, uses a high-dimensional mapping in configuration space to increase overlap.
  arXiv  Detail & Related papers  (2020-02-12T11:10:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.