Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation

• URL: http://arxiv.org/abs/2606.10774v2
• Date: Tue, 16 Jun 2026 01:51:06 GMT
• Title: Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
• Abstract summary: Decentralized Federated Learning enables collaborative model training across wireless edge nodes.<n>We propose DFL-AA, which corrects selection bias using Inverse Probability Weighting and mitigates staleness via Age-of-Information decay.<n>We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines.
• Score: 16.23840462167471
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations. Operating over lossy wireless links under constraints, these systems cannot rely on retransmissions, so model parameters must be accepted as partial chunks, leading to two key failure modes, which are selection bias, where poor-quality links are systematically under-represented in gossip aggregation, and update staleness, where asynchronous nodes contribute outdated models. We prove that classical gossip aggregation introduces irreducible selection bias proportional to the link-loss rate. We propose DFL-AA (Decentralized Federated Learning with Adaptive AoI-weighted Aggregation), which corrects selection bias using Inverse Probability Weighting (IPW) with online channel estimation and mitigates staleness via Age-of-Information (AoI) decay without requiring a global clock. We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines across varying loss rates and heterogeneous channel conditions on fixed directed topologies.

Related papers

• Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks [11.85706685141547]
  We propose CHARGE-FL, a framework that adaptively schedules aggregation based on channel dynamics and application readiness.<n>Results show that CHARGE-FL significantly improves accuracy, stability, and convergence over state-of-the-art OTA-FL methods.
  arXiv  Detail & Related papers  (2026-07-05T10:24:08Z)
• On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach [2.4214594180459366]
  Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale and heterogeneous systems.<n>We propose PushCen-ADFL, a communication-efficient ADFL framework that enables stable training under asymmetric communication and delayed client participation.<n> Experiments on vision datasets demonstrate that PushCen-ADFL improves accuracy under data heterogeneity by up to 6% while reducing per-push communication cost by more than 80%.
  arXiv  Detail & Related papers  (2026-05-24T15:56:37Z)
• Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning [5.14549984289357]
  Over-the-air federated learning (OTA-FL) reduces uplink latency by exploiting waveform superposition.<n>Conventional analog aggregation schemes typically require channel state information (CSI), channel inversion, and coherent phase alignment.
  arXiv  Detail & Related papers  (2026-05-08T05:29:14Z)
• Asynchronous Probability Ensembling for Federated Disaster Detection [0.22870279047711528]
  This paper proposes a decentralized ensembling framework based on asynchronous probability aggregation and feedback distillation.<n>By shifting the exchange unit from model weights to class-probability vectors, our method maintains data privacy, reduces communication requirements by orders of magnitude, and improves overall accuracy.
  arXiv  Detail & Related papers  (2026-04-15T22:01:55Z)
• Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA [61.12136997430116]
  Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via wireless connections for knowledge integration.<n> directly aggregating parameters fine-tuned on heterogeneous datasets induces three primary issues across the DFL life-cycle: (i) catastrophic knowledge forgetting during fine-tuning process, arising from conflicting update directions caused by data heterogeneity; (ii) textitinefficient communication and convergence during model aggregation process,
  arXiv  Detail & Related papers  (2026-02-24T02:45:32Z)
• SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillation [5.14549984289357]
  SCENE is a pilot-free and phase-invariant aggregation primitive for over-the-air federated distillation (OTA-FD)<n>It trades a modest noncoherent variance constant for zero uplink pilots, unbiased aggregation, and hardware-friendly transmission.<n>It can outperform coherent designs when pilot overhead is non-negligible.
  arXiv  Detail & Related papers  (2026-02-17T03:13:32Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA [20.00589625873043]
  textttTAD-LoRA is a serverless variant of federated learning.<n>We show that textttTAD-LoRA is competitive in strongly connected topologies and delivers clear gains under moderately and weakly connected topologies.
  arXiv  Detail & Related papers  (2026-01-31T01:57:53Z)
• OptiVote: Non-Coherent FSO Over-the-Air Majority Vote for Communication-Efficient Distributed Federated Learning in Space Data Centers [68.73273027298625]
  megaconstellations are driving the long-term vision of space data centers (SDCs)<n>AirComp is an in-network aggregation framework for learning free-space (FSO)<n>AirVote integrates sign gradient (SGD) with a majority-signposition modulation (PPM), where each satellite conveys local gradient by activating PPM time slots.<n>OptiVote mitigates phase-sensitive field superposition into phase-agnostic optical intensity combining.
  arXiv  Detail & Related papers  (2025-12-30T16:40:02Z)
• UAV-assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysis [16.963596661873954]
  Hierarchical federated learning (HFL) is a key paradigm to distribute learning across edge devices to reach global intelligence. In HFL, each edge device trains a local model using its respective data and transmits the updated model parameters to an edge server for local aggregation. This paper proposes an unbiased HFL algorithm for unmanned aerial vehicle (UAV)-assisted wireless networks.
  arXiv  Detail & Related papers  (2024-07-05T06:23:01Z)
• Decentralized Federated Learning Over Imperfect Communication Channels [68.08499874460857]
  This paper analyzes the impact of imperfect communication channels on decentralized federated learning (D-FL) It determines the optimal number of local aggregations per training round, adapting to the network topology and imperfect channels. It is seen that D-FL, with an optimal number of local aggregations, can outperform its potential alternatives by over 10% in training accuracy.
  arXiv  Detail & Related papers  (2024-05-21T16:04:32Z)
• Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates [71.81037644563217]
  Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning. As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers. We propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion.
  arXiv  Detail & Related papers  (2024-03-27T09:14:36Z)
• Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networks [60.09912912343705]
  This study explores the benefits of integrating the novel clustered federated learning (CFL) approach with non-independent and identically distributed (non-IID) datasets. A detailed theoretical analysis of the generalization gap that measures the degree of non-IID in the data distribution is presented. Solutions to address the challenges posed by non-IID conditions are proposed with the analysis of the properties.
  arXiv  Detail & Related papers  (2024-03-05T17:49:09Z)
• FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout [14.72932631655587]
  Federated Learning (FL) emerges as a distributed machine learning paradigm without end-user data transmission. FedBIAD provides 2x uplink reduction with an accuracy increase of up to 2.41% even on non-Independent and Identically Distributed (non-IID) data.
  arXiv  Detail & Related papers  (2023-07-14T05:51:04Z)
• Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks [56.91063444859008]
  Federated Learning (FL) is a collaborative machine learning framework that combines on-device training and server-based aggregation. We propose an asynchronous FL design with periodic aggregation to tackle the straggler issue in FL systems. We show that an age-aware'' aggregation weighting design can significantly improve the learning performance in an asynchronous FL setting.
  arXiv  Detail & Related papers  (2022-12-14T17:33:01Z)
• Time-triggered Federated Learning over Wireless Networks [48.389824560183776]
  We present a time-triggered FL algorithm (TT-Fed) over wireless networks. Our proposed TT-Fed algorithm improves the converged test accuracy by up to 12.5% and 5%, respectively.
  arXiv  Detail & Related papers  (2022-04-26T16:37:29Z)
• Towards Efficient and Stable K-Asynchronous Federated Learning with Unbounded Stale Gradients on Non-IID Data [10.299577499118548]
  Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants to train a global model without uploading raw data. This paper proposes a two-stage weighted $K$ asynchronous FL with adaptive learning rate (WKAFL) Experiments implemented on both benchmark and synthetic FL datasets show that WKAFL has better overall performance compared to existing algorithms.
  arXiv  Detail & Related papers  (2022-03-02T16:17:23Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)
• Decentralized Learning for Channel Allocation in IoT Networks over Unlicensed Bandwidth as a Contextual Multi-player Multi-armed Bandit Game [134.88020946767404]
  We study a decentralized channel allocation problem in an ad-hoc Internet of Things network underlaying on the spectrum licensed to a primary cellular network. Our study maps this problem into a contextual multi-player, multi-armed bandit game, and proposes a purely decentralized, three-stage policy learning algorithm through trial-and-error.
  arXiv  Detail & Related papers  (2020-03-30T10:05:35Z)

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.