Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.10957 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916216505892864 |
|---|---|
| author | Cantu-Cervini, Emilio |
| author_facet | Cantu-Cervini, Emilio |
| contents | Traditional Federated Learning (FL) methods typically train a single global model collaboratively without exchanging raw data. In contrast, Personalized Federated Learning (PFL) techniques aim to create multiple models that are better tailored to individual clients' data. We present a novel personalization approach based on stacked generalization where clients directly send each other privacy-preserving models to be used as base models to train a meta-model on private data. Our approach is flexible, accommodating various privacy-preserving techniques and model types, and can be applied in horizontal, hybrid, and vertically partitioned federations. Additionally, it offers a natural mechanism for assessing each client's contribution to the federation. Through comprehensive evaluations across diverse simulated data heterogeneity scenarios, we showcase the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10957 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Personalized Federated Learning via Stacking Cantu-Cervini, Emilio Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing Traditional Federated Learning (FL) methods typically train a single global model collaboratively without exchanging raw data. In contrast, Personalized Federated Learning (PFL) techniques aim to create multiple models that are better tailored to individual clients' data. We present a novel personalization approach based on stacked generalization where clients directly send each other privacy-preserving models to be used as base models to train a meta-model on private data. Our approach is flexible, accommodating various privacy-preserving techniques and model types, and can be applied in horizontal, hybrid, and vertically partitioned federations. Additionally, it offers a natural mechanism for assessing each client's contribution to the federation. Through comprehensive evaluations across diverse simulated data heterogeneity scenarios, we showcase the effectiveness of our method. |
| title | Personalized Federated Learning via Stacking |
| topic | Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2404.10957 |