Coded Over-the-Air Computation for Model Aggregation in Federated Learning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Communications Letters"
DOI: 10.1109/lcomm.2022.3208035
Abstract: This letter introduces a new coded transmission design for model aggregation in federated learning (FL) over Gaussian multiple access channels (MAC), named coded over-the-air computation (codedAirComp). It enjoys the optimality of analog AirComp-based uncoded transmission… read more here.
Keywords: model aggregation; aggregation federated; federated learning; coded air ... See more keywords
Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Communications"
DOI: 10.1109/tcomm.2022.3224977
Abstract: One of the main focuses in distributed learning is communication efficiency, since model aggregation at each round of training can consist of millions to billions of parameters. Several model compression methods, such as gradient quantization… read more here.
Keywords: distortion; model aggregation; rate; communication ... See more keywords
Federated Learning with Lossy Distributed Source Coding: Analysis and Optimization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Communications"
DOI: 10.1109/tcomm.2023.3277882
Abstract: Recently, federated learning (FL), which replaces data sharing with model sharing, has emerged as an efficient and privacy-friendly machine learning (ML) paradigm. One of the main challenges in FL is the huge communication cost for… read more here.
Keywords: model aggregation; aggregation; analysis; convergence ... See more keywords
Towards Class-Balanced Privacy Preserving Heterogeneous Model Aggregation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2022.3183170
Abstract: Heterogeneous model aggregation (HMA) is an effective paradigm that integrates on-device trained models heterogeneous in architecture and target task into a comprehensive model. Recent works adopt knowledge distillation to amalgamate the knowledge of learned features… read more here.
Keywords: model aggregation; heterogeneous model; class; privacy ... See more keywords
Improving Federated Learning With Quality-Aware User Incentive and Auto-Weighted Model Aggregation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Parallel and Distributed Systems"
DOI: 10.1109/tpds.2022.3195207
Abstract: Federated learning enables distributed model training over various computing nodes, e.g., mobile devices, where instead of sharing raw user data, computing nodes can solely commit model updates without compromising data privacy. The quality of federated… read more here.
Keywords: model aggregation; quality; learning quality; federated learning ... See more keywords
Federated Learning via Intelligent Reflecting Surface
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Wireless Communications"
DOI: 10.1109/twc.2021.3099505
Abstract: Over-the-air computation (AirComp) based federated learning (FL) is capable of achieving fast model aggregation by exploiting the waveform superposition property of multiple-access channels. However, the model aggregation performance is severely limited by the unfavorable wireless… read more here.
Keywords: aircomp based; federated learning; model aggregation; intelligent reflecting ... See more keywords