A Novel Privacy Enhancement Scheme with Dynamic Quantization for Federated Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918133091008512 |
|---|---|
| author | Wang, Yifan Cao, Xianghui Jin, Shi Chow, Mo-Yuen |
| author_facet | Wang, Yifan Cao, Xianghui Jin, Shi Chow, Mo-Yuen |
| contents | Federated learning (FL) has been widely regarded as a promising paradigm for privacy preservation of raw data in machine learning. Although, the data privacy in FL is locally protected to some extent, it is still a desideratum to enhance privacy and alleviate communication overhead caused by repetitively transmitting model parameters. Typically, these challenges are addressed separately, or jointly via a unified scheme that consists of noise-injected privacy mechanism and communication compression, which may lead to model corruption due to the introduced composite noise. In this work, we propose a novel model-splitting privacy-preserving FL (MSP-FL) scheme to achieve private FL with precise accuracy guarantee. Based upon MSP-FL, we further propose a model-splitting privacy-preserving FL with dynamic quantization (MSPDQ-FL) to mitigate the communication overhead, which incorporates a shrinking quantization interval to reduce the quantization error. We provide privacy and convergence analysis for both MSP-FL and MSPDQ-FL under non-i.i.d. dataset, partial clients participation and finite quantization level. Numerical results are presented to validate the superiority of the proposed schemes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_16058 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Novel Privacy Enhancement Scheme with Dynamic Quantization for Federated Learning Wang, Yifan Cao, Xianghui Jin, Shi Chow, Mo-Yuen Optimization and Control Federated learning (FL) has been widely regarded as a promising paradigm for privacy preservation of raw data in machine learning. Although, the data privacy in FL is locally protected to some extent, it is still a desideratum to enhance privacy and alleviate communication overhead caused by repetitively transmitting model parameters. Typically, these challenges are addressed separately, or jointly via a unified scheme that consists of noise-injected privacy mechanism and communication compression, which may lead to model corruption due to the introduced composite noise. In this work, we propose a novel model-splitting privacy-preserving FL (MSP-FL) scheme to achieve private FL with precise accuracy guarantee. Based upon MSP-FL, we further propose a model-splitting privacy-preserving FL with dynamic quantization (MSPDQ-FL) to mitigate the communication overhead, which incorporates a shrinking quantization interval to reduce the quantization error. We provide privacy and convergence analysis for both MSP-FL and MSPDQ-FL under non-i.i.d. dataset, partial clients participation and finite quantization level. Numerical results are presented to validate the superiority of the proposed schemes. |
| title | A Novel Privacy Enhancement Scheme with Dynamic Quantization for Federated Learning |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2405.16058 |