Personalized Federated Learning for Generative AI-Assisted Semantic Communications
Not on the map. Why?
Abstract (arXiv)
Semantic Communication (SC) focuses on transmitting only the semantic information rather than the raw data. This approach offers an efficient solution to the issue of spectrum resource utilization caused by the various intelligent applications on Mobile Users (MUs). Generative Artificial Intelligence (GAI) models have recently exhibited remarkable content generation and signal processing capabilities, presenting new opportunities for enhancing SC. Therefore, we propose a GAI-assisted SC (GSC) model deployed between MUs and the Base Station (BS). Then, to train the GSC model using the local data of MUs while ensuring privacy and accommodating heterogeneous requirements of MUs, we introduce Personalized Semantic Federated Learning (PSFL). This approach incorporates a novel Personalized Local Distillation (PLD) and Adaptive Global Pruning (AGP). In PLD, each MU selects a personalized GSC model as a mentor tailored to its local resources and a unified Convolutional Neural Networks (CNN)-based SC (CSC) model as a student. This mentor model is then distilled into the student model for global aggregation. In AGP, we perform network pruning on the aggregated global model according to real-time communication environments, reducing communication energy. Finally, numerical results demonstrate the feasibility and efficiency of the proposed PSFL scheme.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 3 Oct 2024.
Builds on
27 of 37 references.
References · 27
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2021Model-Contrastive Federated Learningcited by 762
- 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
- 2020Deep Learning Enabled Semantic Communication Systemscited by 282
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
- 2019Deep Learning vs. Traditional Computer Visioncited by 94
- 2020Federated Mutual Learningcited by 70
- 2020A Lite Distributed Semantic Communication System for Internet of Thingscited by 69
- 2021Annealing Knowledge Distillationcited by 61
15 more
- 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
- 2022Communication-Efficient Adaptive Federated Learningcited by 55
- 2023Large Language Model Enhanced Multi-Agent Systems for 6G Communicationscited by 53
- 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 40
- 2023Large AI Model Empowered Multimodal Semantic Communicationscited by 38
- 2023Large AI Model-Based Semantic Communicationscited by 35
- 2022Semantic-preserved Communication System for Highly Efficient Speech Transmissioncited by 28
- 2023AI-Generated Incentive Mechanism and Full-Duplex Semantic Communications for Information Sharingcited by 21
- 2022Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoTcited by 15
- 2023Blockchain-aided Secure Semantic Communication for AI-Generated Content in Metaversecited by 15
- 2023Semantic Importance-Aware Communications Using Pre-trained Language Modelscited by 15
- 2022HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networkscited by 12
- 2022Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmissioncited by 12
- 2024Large Generative Model Assisted 3D Semantic Communicationcited by 12
- 2024FedSR: A Semi-Decentralized Federated Learning Algorithm for Non-IIDness in IoT Systemcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.