A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge
[article]
2022
arXiv
pre-print
Federated learning (FL) is a distributed machine learning technology for next-generation AI systems that allows a number of workers, i.e., edge devices, collaboratively learn a shared global model while ...
To address such challenges, this paper aims to accelerate FL convergence over wireless edge by optimizing the multi-hop federated networking performance. ...
Training Coordinator: Federated learning involves nodes with two types of roles, server/aggregator and worker. ...
arXiv:2111.09410v4
fatcat:7ei35rffwrdtbbnbmt3a62v6f4
A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning
2023
Future Internet
As a new distributed machine learning (ML) approach, federated learning (FL) shows great potential to preserve data privacy by enabling distributed data owners to collaboratively build a global model without ...
We firstly design a deep reinforcement learning-assisted FL framework. ...
A well-designed node selection strategy has the potential to improve accuracy, accelerate training speed, and enhance privacy protection, thereby mitigating the limitations of federated learning. ...
doi:10.3390/fi15060209
fatcat:awgatzbjubey3k3bxej4ina34a
Federated Learning in Mobile Edge Computing: An Edge-Learning Perspective for Beyond 5G
[article]
2020
arXiv
pre-print
training efficiency of federated learning. ...
On one hand, we employ machine learning methods to dynamically configure the communication resources in real-time to accelerate the interactions between IoT devices and edge servers, thus improving the ...
Fig. 1 :Fig. 2 : 12 General Resource allocation in communications for Federated Learning
limited
Fig. 3 : 3 Federated Learning under wireless channel constraints commences global model aggregation. ...
arXiv:2007.08030v1
fatcat:zpsonkcmzjb6fb2stvrtzczcxq
MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
[article]
2020
arXiv
pre-print
As a result, continuous local changes may seriously affect the performance of a global model generated by Federated Learning. ...
Since data collection is costly in reality, Google's Federated Learning offers not only complete data privacy but also better model robustness based on multiple user data. ...
To further accelerate the RL learning process, we propose a threshold-based decaying greedy-exploration (TDGE) strategy which extends the existing decaying greedy-exploration (DGE) strategy [38] . ...
arXiv:2002.02897v2
fatcat:vklnhrqpv5d5hpwcbq6tuavodm
FilFL: Accelerating Federated Learning via Client Filtering
[article]
2023
arXiv
pre-print
Federated learning is an emerging machine learning paradigm that enables devices to train collaboratively without exchanging their local data. ...
The above procedure is called client selection which is an important area in federated learning as it highly impacts the convergence rate, learning efficiency, and generalization. ...
Introduction Federated learning (FL) is an emerging machine learning paradigm that organizes collaborative training across distributed clients while keeping their data local (Konečnỳ, 2017; Konečnỳ et ...
arXiv:2302.06599v1
fatcat:z5kyxdqzxjco7dkjbnldrlqqmi
FedSA: Accelerating Intrusion Detection in Collaborative Environments with Federated Simulated Annealing
[article]
2022
arXiv
pre-print
The proposal reduces aggregation rounds and speeds up convergence. Thus, FedSA accelerates learning extraction from local models, requiring fewer IDS updates. ...
This paper proposes the Federated Simulated Annealing (FedSA) metaheuristic to select the hyperparameters and a subset of participants for each aggregation round in federated learning. ...
The first aggregation algorithm for federated learning was Federated Averaging (FedAvg) [9] . The FedAvg does not optimize the federated learning hyperparameters. ...
arXiv:2205.11519v1
fatcat:k6zcuhqnefa6xdiscrdamcqs2a
Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks
[article]
2019
arXiv
pre-print
Federated learning (FL) is a machine learning model that preserves data privacy in the training process. ...
However, since communication usually occurs through a limited spectrum, only a portion of the UEs can update their parameters upon each global aggregation. ...
Here, we tackle the problem via a greedy algorithm. The approach is constituted of two major steps. ...
arXiv:1910.14648v1
fatcat:qwuxgnmrgrebldbg3gxplo6hiu
Asynchronous Hierarchical Federated Learning Based on Bandwidth Allocation and Client Scheduling
2023
Applied Sciences
Federated learning (FL) offers a promising solution in edge computing to overcome bandwidth limitations and privacy concerns associated with traditional cloud-based training. ...
Specifically, we propose an efficient algorithm that dynamically assigns clients to edge servers based on client mobility during training and accelerates parameter uploading while taking into account the ...
Previous time-current time via greedy optimization algorithm. ...
doi:10.3390/app132011134
fatcat:ztf4mxuqyrce3d6b64d5isdtti
Adaptive Federated Learning and Digital Twin for Industrial Internet of Things
[article]
2020
arXiv
pre-print
We adaptively adjust the aggregation frequency of federated learning based on Lyapunov dynamic deficit queue and deep reinforcement learning, to improve the learning performance under the resource constraints ...
Noticing that digital twins may bring estimation deviations from the actual value of device state, a trusted based aggregation is proposed in federated learning to alleviate the effects of such deviation ...
The federated learning with DT deviation calibrated by the trust weighted aggregation strategy can achieve higher accuracy than the federated learning with the DT deviation, and the federated learning ...
arXiv:2010.13058v2
fatcat:gfu2vkpucva5rb554lr7vqcklu
Fuzzy Logic based Client Selection for Federated Learning in Vehicular Networks
2022
IEEE Open Journal of the Computer Society
Federated learning is a promising paradigm for achieving distributed intelligence by protecting user privacy in vehicular networks. ...
RELATED WORK Regarding the client selection of federated learning, some approaches are proposed, including biased client selection [7] , unbiased client selection [8] - [10] , synchronous aggregation ...
Workflow of federated learning.
. The global model is disseminated to the clients. ...
doi:10.1109/ojcs.2022.3163620
fatcat:ocqwtwdoe5c7pfsrncfras5jvi
Towards asynchronous federated learning for heterogeneous edge-powered internet of things
2021
Digital Communications and Networks
Federated learning, a distributed machine learning framework, is a promising solution to train machine learning models with resource-limited devices and edge servers. ...
Particularly, we formulate an asynchronous federated learning model and develop a lightweight node selection algorithm to carry out learning tasks effectively. ...
Additionally, our proposed scheme has low computing complexity via using a greedy based method. ...
doi:10.1016/j.dcan.2021.04.001
fatcat:m5ngbomonfcpdj6cast4l67z6y
Computation and Privacy Protection for Satellite-Ground Digital Twin Networks
[article]
2023
arXiv
pre-print
Next, we propose a Lyapunov stability theory-based model-agnostic metalearning aided multi-agent deep federated reinforcement learning (MAML-MADFRL) framework for optimizing the CPU cycle frequency, channel ...
average penalty, and fulfill the long-term average queue size via lower computational complexity. ...
Meanwhile, tasks are offloaded to LEO to relieve computation pressure while protecting data privacy via federated aggregation and issuing mechanisms. ...
arXiv:2302.08525v1
fatcat:myv4fsbljbgejm7kplpdoh4adq
Recent Advances on Federated Learning: A Systematic Survey
[article]
2023
arXiv
pre-print
Federated learning has emerged as an effective paradigm to achieve privacy-preserving collaborative learning among different parties. ...
First, we present a new taxonomy of federated learning in terms of the pipeline and challenges in federated scenarios. ...
Secure federated learning The original design of federated learning considers the security problem via exchanging parameters while keeping raw data in their own devices. ...
arXiv:2301.01299v1
fatcat:343minsl7fhmtgtguqh4q2chru
Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learning
[article]
2021
arXiv
pre-print
In this paper, we study asynchronous federated learning (FL) in a wireless distributed learning network (WDLN). ...
in terms of model accuracy, training loss, learning speed, and robustness of learning. ...
Due to the emergence of the need for distributed learning, federated learning (FL) has been widely studied as a potentially viable solution for distributed learning [1] , [2] . coordination of a central ...
arXiv:2103.01422v2
fatcat:ayhqmsxearhe3daosqbkhxfgry
Efficient Federated Meta-Learning over Multi-Access Wireless Networks
[article]
2021
arXiv
pre-print
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. ...
Further, we show that the computational complexity of NUFM can be reduced from O(d^2) to O(d) (with the model dimension d) via combining two first-order approximation techniques. ...
Standard Algorithm Similar to federated learning, vanilla FML algorithm solves (1) in two repeating steps: local update and global aggregation [9] , as detailed below. ...
arXiv:2108.06453v4
fatcat:4wxomov46bce7ddxobqtkllak4
« Previous
Showing results 1 — 15 out of 1,522 results