Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead

• URL: http://arxiv.org/abs/2509.22174v1
• Date: Fri, 26 Sep 2025 10:34:06 GMT
• Title: Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead
• Authors: Durgesh Kalwar, Mayank Baranwal, Harshad Khadilkar,
• Abstract summary: We introduce DYNAWEIGHT, a novel framework to information aggregation in multi-agent networks.<n> DYNAWEIGHT dynamically allocates weights to neighboring servers based on their relative losses on local datasets.
• Score: 3.485627109660862
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes especially crucial within fully decentralized infrastructures where local processing is imperative due to the absence of centralized aggregation. Here, we introduce DYNAWEIGHT, a novel framework to information aggregation in multi-agent networks. DYNAWEIGHT offers substantial acceleration in decentralized learning with minimal additional communication and memory overhead. Unlike traditional static weight assignments, such as Metropolis weights, DYNAWEIGHT dynamically allocates weights to neighboring servers based on their relative losses on local datasets. Consequently, it favors servers possessing diverse information, particularly in scenarios of substantial data heterogeneity. Our experiments on various datasets MNIST, CIFAR10, and CIFAR100 incorporating various server counts and graph topologies, demonstrate notable enhancements in training speeds. Notably, DYNAWEIGHT functions as an aggregation scheme compatible with any underlying server-level optimization algorithm, underscoring its versatility and potential for widespread integration.

Related papers

• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Power Grid Control with Graph-Based Distributed Reinforcement Learning [60.49805771047161]
  This work advances a graph-based distributed reinforcement learning framework for real-time, scalable grid management.<n>A Graph Neural Network (GNN) is employed to encode the network's topological information within the single low-level agent's observation.<n>Experiments on the Grid2Op simulation environment show the effectiveness of the approach.
  arXiv  Detail & Related papers  (2025-09-02T22:17:25Z)
• Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning [0.48342038441006796]
  Federated learning (FL) is a subfield of machine learning that avoids sharing local data with a central server.<n>In FL, fusing locally-trained models with unbalanced datasets may deteriorate the performance of global model aggregation.<n>We introduce an Optimal Transport-based preprocessing algorithm that aligns the datasets by minimizing the distributional discrepancy of data along the edge devices.
  arXiv  Detail & Related papers  (2025-06-04T15:35:55Z)
• Semi-decentralized Training of Spatio-Temporal Graph Neural Networks for Traffic Prediction [0.15978270011184256]
  We explore and adapt semi-decentralized training techniques for Spatiotemporal Graph-Temporal Neural Networks (ST-GNNs) in smart mobility domain.<n>We implement a simulation framework where sensors are grouped by proximity into multiple cloudlets.<n>We show that semi-decentralized setups are comparable to centralized approaches in performance metrics.
  arXiv  Detail & Related papers  (2024-12-04T10:20:21Z)
• SCALE: Self-regulated Clustered federAted LEarning in a Homogeneous Environment [4.925906256430176]
  Federated Learning (FL) has emerged as a transformative approach for enabling distributed machine learning while preserving user privacy. This paper presents a novel FL methodology that overcomes these limitations by eliminating the dependency on edge servers.
  arXiv  Detail & Related papers  (2024-07-25T20:42:16Z)
• Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity [14.313847382199059]
  Federated quantization-based self-supervised learning scheme (Fed-QSSL) designed to address heterogeneity in FL systems. Fed-QSSL deploys de-quantization, weighted aggregation and re-quantization, ultimately creating models personalized to both data distribution and specific infrastructure of each client's device.
  arXiv  Detail & Related papers  (2023-12-20T19:11:19Z)
• Clustered Federated Learning via Generalized Total Variation Minimization [83.26141667853057]
  We study optimization methods to train local (or personalized) models for local datasets with a decentralized network structure. Our main conceptual contribution is to formulate federated learning as total variation minimization (GTV) Our main algorithmic contribution is a fully decentralized federated learning algorithm.
  arXiv  Detail & Related papers  (2021-05-26T18:07:19Z)
• Reinforcement Learning for Datacenter Congestion Control [50.225885814524304]
  Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such learning-based algorithms have shown practical potential in this domain. We devise an RL-based algorithm with the aim of generalizing to different configurations of real-world datacenter networks. We show that this scheme outperforms alternative popular RL approaches, and generalizes to scenarios that were not seen during training.
  arXiv  Detail & Related papers  (2021-02-18T13:49:28Z)
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data [77.88594632644347]
  Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge. We propose a novel momentum-based method to mitigate this decentralized training difficulty.
  arXiv  Detail & Related papers  (2021-02-09T11:27:14Z)
• Dif-MAML: Decentralized Multi-Agent Meta-Learning [54.39661018886268]
  We propose a cooperative multi-agent meta-learning algorithm, referred to as MAML or Dif-MAML. We show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.
  arXiv  Detail & Related papers  (2020-10-06T16:51:09Z)
• Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks [8.456633924613456]
  Federated learning (FL) is emerging as a new paradigm to train machine learning models in distributed systems. The paper proposes a fully distributed (or server-less) learning approach: the proposed FL algorithms leverage the cooperation of devices that perform data operations inside the network. The approach lays the groundwork for integration of FL within 5G and beyond networks characterized by decentralized connectivity and computing.
  arXiv  Detail & Related papers  (2019-12-27T15:16:04Z)

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.