{"id":68,"date":"2024-05-13T15:55:13","date_gmt":"2024-05-13T15:55:13","guid":{"rendered":"http:\/\/wp.well-e.org\/?page_id=68"},"modified":"2026-01-22T14:14:12","modified_gmt":"2026-01-22T19:14:12","slug":"conferences-et-ateliers","status":"publish","type":"page","link":"https:\/\/wp.well-e.org\/en\/conferences-et-ateliers\/","title":{"rendered":"Conferences and workshops"},"content":{"rendered":"\n
<\/a>
\r\n
87 entries<\/span> \u00ab<\/a> \u2039<\/a> 1 of 2 \u203a<\/a> \u00bb<\/a> <\/div><\/div>

Driss, Marayam Ben; Sabir, Essaid; Elbiaze, Halima; Diallo, Abdoulaye Banir\u00e9<\/p>

Fast & Energy Efficient Federated Learning Using Multi-Attribute Client Clustering and Selection<\/a> Proceedings Article<\/span> <\/p>

In: <\/span>Taipei, Taiwan, <\/span>2025<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span> | Tags: <\/span><\/p>

@inproceedings{ben_driss_fast_2025,
\r\ntitle = {Fast & Energy Efficient Federated Learning Using Multi-Attribute Client Clustering and Selection},
\r\nauthor = {Marayam Ben Driss and Essaid Sabir and Halima Elbiaze and Abdoulaye Banir\u00e9 Diallo},
\r\nurl = {https:\/\/ieeexplore.ieee.org\/abstract\/document\/11174476},
\r\ndoi = {10.1109\/VTC2025-Spring65109.2025.11174476},
\r\nyear  = {2025},
\r\ndate = {2025-12-01},
\r\naddress = {Taipei, Taiwan},
\r\nabstract = {Federated Learning (FL) presents a promising paradigm for decentralized model training; however, its real-world adoption is hindered by several critical challenges, including non-independent and identically distributed (non-IID) data across clients, heterogeneous computational capabilities, and significant communication overhead. To address these issues, this paper introduces a novel multi-attribute client clustering and selection framework for FL. The proposed approach groups clients according to data distribution, device capabilities, geographic location, and model update behavior. Within each cluster, an adaptive client selection mechanism leverages dynamic attributes such as residual energy, data freshness, and client participation motivation to identify the most suitable participants. Experimental evaluations on standard FL benchmark datasets demonstrate that the proposed framework achieves faster convergence, higher global model accuracy, and improved energy efficiency compared to state-of-the-art approaches.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {inproceedings}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
Federated Learning (FL) presents a promising paradigm for decentralized model training; however, its real-world adoption is hindered by several critical challenges, including non-independent and identically distributed (non-IID) data across clients, heterogeneous computational capabilities, and significant communication overhead. To address these issues, this paper introduces a novel multi-attribute client clustering and selection framework for FL. The proposed approach groups clients according to data distribution, device capabilities, geographic location, and model update behavior. Within each cluster, an adaptive client selection mechanism leverages dynamic attributes such as residual energy, data freshness, and client participation motivation to identify the most suitable participants. Experimental evaluations on standard FL benchmark datasets demonstrate that the proposed framework achieves faster convergence, higher global model accuracy, and improved energy efficiency compared to state-of-the-art approaches.<\/div>
Close<\/a><\/p><\/div>