FTTE: Federated Learning on Resource-Constrained Devices

• URL: http://arxiv.org/abs/2510.03165v1
• Date: Fri, 03 Oct 2025 16:36:09 GMT
• Title: FTTE: Federated Learning on Resource-Constrained Devices
• Abstract summary: Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy.<n>Traditional synchronous and asynchronous FL approaches suffer from straggler induced delays and slow convergence in heterogeneous, large scale networks.<n>We present FTTE (Federated Tiny Training Engine),a novel semi-asynchronous FL framework that employs sparse parameter updates and a staleness-weighted aggregation.
• Score: 1.3474501014756581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy, but deployment on resource-constrained edge nodes remains challenging due to limited memory, energy, and communication bandwidth. Traditional synchronous and asynchronous FL approaches further suffer from straggler induced delays and slow convergence in heterogeneous, large scale networks. We present FTTE (Federated Tiny Training Engine),a novel semi-asynchronous FL framework that uniquely employs sparse parameter updates and a staleness-weighted aggregation based on both age and variance of client updates. Extensive experiments across diverse models and data distributions - including up to 500 clients and 90% stragglers - demonstrate that FTTE not only achieves 81% faster convergence, 80% lower on-device memory usage, and 69% communication payload reduction than synchronous FL (eg.FedAVG), but also consistently reaches comparable or higher target accuracy than semi-asynchronous (eg.FedBuff) in challenging regimes. These results establish FTTE as the first practical and scalable solution for real-world FL deployments on heterogeneous and predominantly resource-constrained edge devices.

Related papers

• HybridFLow: SDN-Orchestrated Client Partitioning for Hybrid Federated Learning [3.1437837429431155]
  Cross-silo Federated Learning (FL) enables geographically distributed institutions to collaboratively train machine learning models without sharing raw data.<n>We present HybridFLow, a closed-loop SDN-driven orchestration framework that integrates network-layer intelligence directly into hybrid FL.
  arXiv  Detail & Related papers  (2026-09-09T16:23:53Z)
• Adaptive Deadline and Batch Layered Synchronized Federated Learning [66.93447103966439]
  Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner.<n>We propose ADEL-FL, a novel framework that jointly optimize per-round deadlines and user-specific batch sizes for layer-wise aggregation.
  arXiv  Detail & Related papers  (2025-05-29T19:59:18Z)
• FRAIN to Train: A Fast-and-Reliable Solution for Decentralized Federated Learning [1.1510009152620668]
  asynchronous learning (FL) enables collaborative model training across distributed clients while preserving data locality.<n>We introduce Fast-and-Reliable AI Network, FRAIN, a new FL method that mitigates these limitations by incorporating two key ideas.<n>Experiments with a CNN image-classification model and a Transformer-based language model demonstrate that FRAIN achieves more stable and robust convergence than FedAvg, FedAsync, and BRAIN.
  arXiv  Detail & Related papers  (2025-05-07T08:20:23Z)
• Hyperdimensional Computing Empowered Federated Foundation Model over Wireless Networks for Metaverse [56.384390765357004]
  We propose an integrated federated split learning and hyperdimensional computing framework for emerging foundation models. This novel approach reduces communication costs, computation load, and privacy risks, making it suitable for resource-constrained edge devices in the Metaverse.
  arXiv  Detail & Related papers  (2024-08-26T17:03:14Z)
• FedAST: Federated Asynchronous Simultaneous Training [27.492821176616815]
  Federated Learning (FL) enables devices or clients to collaboratively train machine learning (ML) models without sharing their private data. Much of the existing work in FL focuses on efficiently learning a model for a single task. In this paper, we propose simultaneous training of multiple FL models using a common set of datasets.
  arXiv  Detail & Related papers  (2024-06-01T05:14:20Z)
• Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks [72.59891661768177]
  Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device.
  arXiv  Detail & Related papers  (2023-09-04T21:10:45Z)
• Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity [72.85248553787538]
  This paper focuses on performance analysis and optimization for wireless FL, considering data heterogeneity, combined with wireless resource allocation. We formulate the loss function minimization problem, under constraints on long-term energy consumption and latency, and jointly optimize client scheduling, resource allocation, and the number of local training epochs (CRE) Experiments on real-world datasets demonstrate that the proposed algorithm outperforms other benchmarks in terms of the learning accuracy and energy consumption.
  arXiv  Detail & Related papers  (2023-08-04T04:18:01Z)
• FAVANO: Federated AVeraging with Asynchronous NOdes [14.412305295989444]
  We propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource constrained environments.
  arXiv  Detail & Related papers  (2023-05-25T14:30:17Z)
• HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse [49.1501082763252]
  This paper presents HFEDMS for incorporating practical FL into the emerging Industrial Metaverse. It reduces data heterogeneity through dynamic grouping and training mode conversion. Then, it compensates for the forgotten knowledge by fusing compressed historical data semantics. Experiments have been conducted on the streamed non-i.i.d. FEMNIST dataset using 368 simulated devices.
  arXiv  Detail & Related papers  (2022-11-07T04:33:24Z)
• SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication [11.763368822546468]
  We show that SWIFT converges faster with respect to run-time due to its wait-free structure. SWIFT produces loss levels for image classification, over IID and non-IID data settings, upwards 50% faster than existing SOTA algorithms.
  arXiv  Detail & Related papers  (2022-10-25T14:01:21Z)
• 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)

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.