Federated Learning on Riemannian Manifolds with Differential Privacy
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_ | 1866910411778949120 |
|---|---|
| author | Huang, Zhenwei Huang, Wen Jawanpuria, Pratik Mishra, Bamdev |
| author_facet | Huang, Zhenwei Huang, Wen Jawanpuria, Pratik Mishra, Bamdev |
| contents | In recent years, federated learning (FL) has emerged as a prominent paradigm in distributed machine learning. Despite the partial safeguarding of agents' information within FL systems, a malicious adversary can potentially infer sensitive information through various means. In this paper, we propose a generic private FL framework defined on Riemannian manifolds (PriRFed) based on the differential privacy (DP) technique. We analyze the privacy guarantee while establishing the convergence properties. To the best of our knowledge, this is the first federated learning framework on Riemannian manifold with a privacy guarantee and convergence results. Numerical simulations are performed on synthetic and real-world datasets to showcase the efficacy of the proposed PriRFed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10029 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Learning on Riemannian Manifolds with Differential Privacy Huang, Zhenwei Huang, Wen Jawanpuria, Pratik Mishra, Bamdev Optimization and Control Cryptography and Security Machine Learning 68W15, 68P27, 90C30, 90C48 In recent years, federated learning (FL) has emerged as a prominent paradigm in distributed machine learning. Despite the partial safeguarding of agents' information within FL systems, a malicious adversary can potentially infer sensitive information through various means. In this paper, we propose a generic private FL framework defined on Riemannian manifolds (PriRFed) based on the differential privacy (DP) technique. We analyze the privacy guarantee while establishing the convergence properties. To the best of our knowledge, this is the first federated learning framework on Riemannian manifold with a privacy guarantee and convergence results. Numerical simulations are performed on synthetic and real-world datasets to showcase the efficacy of the proposed PriRFed approach. |
| title | Federated Learning on Riemannian Manifolds with Differential Privacy |
| topic | Optimization and Control Cryptography and Security Machine Learning 68W15, 68P27, 90C30, 90C48 |
| url | https://arxiv.org/abs/2404.10029 |