FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916206581121024 |
|---|---|
| author | Yi, Kai Gazagnadou, Nidham Richtárik, Peter Lyu, Lingjuan |
| author_facet | Yi, Kai Gazagnadou, Nidham Richtárik, Peter Lyu, Lingjuan |
| contents | The interest in federated learning has surged in recent research due to its unique ability to train a global model using privacy-secured information held locally on each client. This paper pays particular attention to the issue of client-side model heterogeneity, a pervasive challenge in the practical implementation of FL that escalates its complexity. Assuming a scenario where each client possesses varied memory storage, processing capabilities and network bandwidth - a phenomenon referred to as system heterogeneity - there is a pressing need to customize a unique model for each client. In response to this, we present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning, tailored for model heterogeneity scenarios. Our proposed methodology can incorporate and adapt well-established techniques to its specific instances. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09816 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity Yi, Kai Gazagnadou, Nidham Richtárik, Peter Lyu, Lingjuan Machine Learning Cryptography and Security The interest in federated learning has surged in recent research due to its unique ability to train a global model using privacy-secured information held locally on each client. This paper pays particular attention to the issue of client-side model heterogeneity, a pervasive challenge in the practical implementation of FL that escalates its complexity. Assuming a scenario where each client possesses varied memory storage, processing capabilities and network bandwidth - a phenomenon referred to as system heterogeneity - there is a pressing need to customize a unique model for each client. In response to this, we present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning, tailored for model heterogeneity scenarios. Our proposed methodology can incorporate and adapt well-established techniques to its specific instances. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies. |
| title | FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2404.09816 |