HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetwork
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916144621813760 |
|---|---|
| author | Chen, Xingyun Huang, Yan Xie, Zhenzhen Pang, Junjie |
| author_facet | Chen, Xingyun Huang, Yan Xie, Zhenzhen Pang, Junjie |
| contents | In response to the challenges posed by non-independent and identically distributed (non-IID) data and the escalating threat of privacy attacks in Federated Learning (FL), we introduce HyperFedNet (HFN), a novel architecture that incorporates hypernetworks to revolutionize parameter aggregation and transmission in FL. Traditional FL approaches, characterized by the transmission of extensive parameters, not only incur significant communication overhead but also present vulnerabilities to privacy breaches through gradient analysis. HFN addresses these issues by transmitting a concise set of hypernetwork parameters, thereby reducing communication costs and enhancing privacy protection. Upon deployment, the HFN algorithm enables the dynamic generation of parameters for the basic layer of the FL main network, utilizing local database features quantified by embedding vectors as input. Through extensive experimentation, HFN demonstrates superior performance in reducing communication overhead and improving model accuracy compared to conventional FL methods. By integrating the HFN algorithm into the FL framework, HFN offers a solution to the challenges of non-IID data and privacy threats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18445 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetwork Chen, Xingyun Huang, Yan Xie, Zhenzhen Pang, Junjie Networking and Internet Architecture In response to the challenges posed by non-independent and identically distributed (non-IID) data and the escalating threat of privacy attacks in Federated Learning (FL), we introduce HyperFedNet (HFN), a novel architecture that incorporates hypernetworks to revolutionize parameter aggregation and transmission in FL. Traditional FL approaches, characterized by the transmission of extensive parameters, not only incur significant communication overhead but also present vulnerabilities to privacy breaches through gradient analysis. HFN addresses these issues by transmitting a concise set of hypernetwork parameters, thereby reducing communication costs and enhancing privacy protection. Upon deployment, the HFN algorithm enables the dynamic generation of parameters for the basic layer of the FL main network, utilizing local database features quantified by embedding vectors as input. Through extensive experimentation, HFN demonstrates superior performance in reducing communication overhead and improving model accuracy compared to conventional FL methods. By integrating the HFN algorithm into the FL framework, HFN offers a solution to the challenges of non-IID data and privacy threats. |
| title | HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetwork |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2402.18445 |