FedShift: Tackling Dual Heterogeneity Problem of Federated Learning via
Weight Shift Aggregation
- URL: http://arxiv.org/abs/2402.01070v1
- Date: Fri, 2 Feb 2024 00:03:51 GMT
- Title: FedShift: Tackling Dual Heterogeneity Problem of Federated Learning via
Weight Shift Aggregation
- Authors: Jungwon Seo, Chunming Rong, Minhoe Kim
- Abstract summary: Federated Learning (FL) offers a compelling method for training machine learning models with a focus on preserving data privacy.
The presence of system heterogeneity and statistical heterogeneity, recognized challenges in FL, arises from the diversity of client hardware, network, and dataset distribution.
This paper introduces FedShift, a novel algorithm designed to enhance both the training speed and the models' accuracy in a dual heterogeneous scenario.
- Score: 6.3842184099869295
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated Learning (FL) offers a compelling method for training machine
learning models with a focus on preserving data privacy. The presence of system
heterogeneity and statistical heterogeneity, recognized challenges in FL,
arises from the diversity of client hardware, network, and dataset
distribution. This diversity can critically affect the training pace and the
performance of models. While many studies address either system or statistical
heterogeneity by introducing communication-efficient or stable convergence
algorithms, addressing these challenges in isolation often leads to compromises
due to unaddressed heterogeneity. In response, this paper introduces FedShift,
a novel algorithm designed to enhance both the training speed and the models'
accuracy in a dual heterogeneity scenario. Our solution can improve client
engagement through quantization and mitigate the adverse effects on performance
typically associated with quantization by employing a shifting technique. This
technique has proven to enhance accuracy by an average of 3.9% in diverse
heterogeneity environments.
Related papers
- Over-the-Air Fair Federated Learning via Multi-Objective Optimization [52.295563400314094]
We propose an over-the-air fair federated learning algorithm (OTA-FFL) to train fair FL models.
Experiments demonstrate the superiority of OTA-FFL in achieving fairness and robust performance.
arXiv Detail & Related papers (2025-01-06T21:16:51Z) - 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) - AEDFL: Efficient Asynchronous Decentralized Federated Learning with
Heterogeneous Devices [61.66943750584406]
We propose an Asynchronous Efficient Decentralized FL framework, i.e., AEDFL, in heterogeneous environments.
First, we propose an asynchronous FL system model with an efficient model aggregation method for improving the FL convergence.
Second, we propose a dynamic staleness-aware model update approach to achieve superior accuracy.
Third, we propose an adaptive sparse training method to reduce communication and computation costs without significant accuracy degradation.
arXiv Detail & Related papers (2023-12-18T05:18:17Z) - Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients.
FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification.
Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
arXiv Detail & Related papers (2023-05-01T20:04:46Z) - 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) - Performance Optimization for Variable Bitwidth Federated Learning in
Wireless Networks [103.22651843174471]
This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization.
In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which aggregates them into a quantized global model and synchronizes the devices.
We show that the FL training process can be described as a Markov decision process and propose a model-based reinforcement learning (RL) method to optimize action selection over iterations.
arXiv Detail & Related papers (2022-09-21T08:52:51Z) - AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias
Estimation [12.62716075696359]
In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data.
In order to estimate and therefore remove this drift, variance reduction techniques have been incorporated into FL optimization recently.
We propose an adaptive algorithm that accurately estimates drift across clients.
arXiv Detail & Related papers (2022-04-27T20:04:24Z) - Optimizing the Communication-Accuracy Trade-off in Federated Learning
with Rate-Distortion Theory [1.5771347525430772]
A significant bottleneck in federated learning is the network communication cost of sending model updates from client devices to the central server.
Our method encodes quantized updates with an appropriate universal code, taking into account their empirical distribution.
Because quantization introduces error, we select quantization levels by optimizing for the desired trade-off in average total gradient and distortion.
arXiv Detail & Related papers (2022-01-07T20:17:33Z) - 1-Bit Compressive Sensing for Efficient Federated Learning Over the Air [32.14738452396869]
This paper develops and analyzes a communication-efficient scheme for learning (FL) over the air, which incorporates 1-bit sensing (CS) into analog aggregation transmissions.
For scalable computing, we develop an efficient implementation that is suitable for large-scale networks.
Simulation results show that our proposed 1-bit CS based FL over the air achieves comparable performance to the ideal case.
arXiv Detail & Related papers (2021-03-30T03:50:31Z)
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.