Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Canh T. Dinh"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. :1-11
Non-independent and identically distributed (non-IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL). Several approaches to handle non-IID data, such as personalized FL and fed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79f9021dee7b6b49527c6415018047c4
https://doi.org/10.1109/tnnls.2022.3224252
https://doi.org/10.1109/tnnls.2022.3224252
Autor:
Duy T. Ngo, Nguyen H. Tran, Canh T. Dinh, Tuan-Anh Le, Amir Rezaei Balef, Tuan Dung Nguyen, Phuong Luu Vo
Publikováno v:
IEEE Communications Letters. 25:3282-3286
Transferring large models in federated learning (FL) networks is often hindered by clients’ limited bandwidth. We propose $\textsf {FedAA}$ , an FL algorithm which achieves fast convergence by exploiting the regularized Anderson acceleration (AA) o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b88b1ef8bf9ccf23695624a197c6e26d
https://doi.org/10.1109/lcomm.2021.3103536
https://doi.org/10.1109/lcomm.2021.3103536
Publikováno v:
Vu, T T, Van Chien, T, Dinh, C T, Ngo, H-Q & Matthaiou, M 2022, Channel estimation in RIS-assisted downlink massive MIMO: a learning-based approach . in 2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC): Proceedings . IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/SPAWC51304.2022.9834023
2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)
2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)
For downlink massive multiple-input multiple-output (MIMO) operating in time-division duplex protocol, users can decode the signals effectively by only utilizing the channel statistics as long as channel hardening holds. However, in a reconfigurable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86db082e88dba8584a3ac97a5436939c
https://doi.org/10.1109/spawc51304.2022.9834023
https://doi.org/10.1109/spawc51304.2022.9834023
Publikováno v:
ICPP
Federated Learning (FL) is a fast-developing distributed machine learning technique involving the participation of a massive number of user devices. While FL has benefits of data privacy and the abundance of user-generated data, its challenges of het
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a04757e124351946579286974be00b64
https://doi.org/10.1145/3404397.3404457
https://doi.org/10.1145/3404397.3404457
Autor:
Choong Seon Hong, Nguyen H. Tran, Canh T. Dinh, Minh N. H. Nguyen, Albert Y. Zomaya, Vincent Gramoli, Wei Bao
There is an increasing interest in a fast-growing machine learning technique called Federated Learning, in which the model training is distributed over mobile user equipments (UEs), exploiting UEs' local computation and training data. Despite its adv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec5aa1c3790602a350205ee1ee877507
Publikováno v:
2016 International Conference on Computer Communication and Informatics (ICCCI).
High Efficiency Video Coding (HEVC) or H.265Standard fulfills the demand of high resolution video storage and transmission since it achieves high compression ratio. However, it requires a huge amount of calculation. Since Motion Estimation (ME) block
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::119230d1b831358a462ba4a6ac89042b
https://doi.org/10.1109/iccci.2016.7479971
https://doi.org/10.1109/iccci.2016.7479971