Please use this identifier to cite or link to this item:
https://bura.brunel.ac.uk/handle/2438/31734Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Peng, Yubo | - |
| dc.contributor.author | Jiang, Feibo | - |
| dc.contributor.author | Dong, Li | - |
| dc.contributor.author | Wang, Kezhi | - |
| dc.contributor.author | Yang, Kun | - |
| dc.date.accessioned | 2025-08-13T09:48:46Z | - |
| dc.date.available | 2025-08-13T09:48:46Z | - |
| dc.date.issued | 2025-07-08 | - |
| dc.identifier | ORCiD: Yubo Peng https://orcid.org/0000-0001-9684-2971 | - |
| dc.identifier | ORCiD: Feibo Jiang https://orcid.org/0000-0002-0235-0253 | - |
| dc.identifier | ORCiD: Li Dong https://orcid.org/0000-0002-0127-8480 | - |
| dc.identifier | ORCiD: Kezhi Wang https://orcid.org/0000-0001-8602-0800 | - |
| dc.identifier | ORCiD: Kun Yang https://orcid.org/0000-0002-6782-6689 | - |
| dc.identifier.citation | Peng, Y. et al. (2026) 'Personalized Federated Learning for GAI-Assisted Semantic Communications', IEEE Transactions on Cognitive Communications and Networking, 12, pp. 2513–2525. doi: 10.1109/TCCN.2025.3586904. | en_US |
| dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/31734 | - |
| dc.description.abstract | Semantic Communication (SC), which focuses on transmitting meaning rather than raw data, has emerged as the next-generation communication paradigm. However, the performance of SC is heavily influenced by network design and training methodologies. To address these challenges and enhance SC performance at the edge, we first introduce a Generative Artificial Intelligence (GAI)-assisted SC (GSC) model, which improves SC capabilities by optimizing the network architecture. Then, to achieve the efficient learning of GSC models deployed on each user, a Personalized Semantic Federated Learning (PSFL) framework is proposed. Specifically, in the local training phase, a Personalized Local Distillation (PLD) approach is employed, where each user selects a tailored GSC model as a mentor based on local resources. This mentor subsequently distills knowledge to a unified student model, ensuring compliance with the model isomorphism requirements of FL. In the global aggregation phase, an Adaptive Global Pruning (AGP) scheme is applied, dynamically pruning or expanding the aggregated global model based on real-time channel conditions. This mechanism effectively balances accuracy and communication energy efficiency. Finally, numerical results validate the feasibility and efficacy of the proposed PSFL framework, demonstrating its potential to enhance SC performance in edge environments significantly. | en_US |
| dc.description.sponsorship | Jiangsu Major Project on Basic Research (Grant Number: BK20243059) | en_US |
| dc.description.sponsorship | Gusu Innovation Project (Grant Number: ZXL2024360) | - |
| dc.description.sponsorship | 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62132004) | - |
| dc.description.sponsorship | Major Program Project of Xiangjiang Laboratory (Grant Number: XJ2023001 and XJ2022001) | - |
| dc.description.sponsorship | Qiyuan Lab Innovation Fund (Grant Number: 2022-JCJQ-LA-001-088) | - |
| dc.format.extent | pp. 2513–2525 | - |
| dc.format.medium | Electronic | - |
| dc.language | English | en_US |
| dc.language.iso | en_US | en_US |
| dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
| dc.rights | Re-use licence for this version: InCopyright | - |
| dc.rights | Licence for published version: Publisher's own licence | - |
| dc.rights.uri | https://rightsstatements.org/page/InC/1.0/ | - |
| dc.subject | semantic communication | en_US |
| dc.subject | federated learning | en_US |
| dc.subject | generative artificial intelligence | en_US |
| dc.subject | network pruning | en_US |
| dc.title | Personalized Federated Learning for GAI-Assisted Semantic Communications | en_US |
| dc.type | Article | en_US |
| dc.date.dateAccepted | 2025-06-28 | - |
| dc.identifier.doi | https://doi.org/10.1109/TCCN.2025.3586904 | - |
| dc.relation.isPartOf | IEEE Transactions on Cognitive Communications and Networking | en_US |
| pubs.publication-status | Published | - |
| pubs.volume | 12 | - |
| dc.identifier.eissn | 2332-7731 | - |
| dcterms.dateAccepted | 2025-06-28 | - |
| dcterms.issued | 2025-07-08 | - |
| dc.rights.holder | Institute of Electrical and Electronics Engineers (IEEE) | - |
| dc.contributor.orcid | Peng, Yubo [0000-0001-9684-2971] | - |
| dc.contributor.orcid | Jiang, Feibo [0000-0002-0235-0253] | - |
| dc.contributor.orcid | Dong, Li [0000-0002-0127-8480] | - |
| dc.contributor.orcid | Wang, Kezhi [0000-0001-8602-0800] | - |
| dc.contributor.orcid | Yang, Kun [0000-0002-6782-6689] | - |
| Appears in Collections: | Department of Computer Science Research Papers | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| FullText.pdf | Copyright © 2025 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works ( https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/ ). | 12.69 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.