IP-FL: Incentivized and Personalized Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929536320405504 |
|---|---|
| author | Khan, Ahmad Faraz Wang, Xinran Le, Qi Abdeen, Zain ul Khan, Azal Ahmad Ali, Haider Jin, Ming Ding, Jie Butt, Ali R. Anwar, Ali |
| author_facet | Khan, Ahmad Faraz Wang, Xinran Le, Qi Abdeen, Zain ul Khan, Azal Ahmad Ali, Haider Jin, Ming Ding, Jie Butt, Ali R. Anwar, Ali |
| contents | Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentives such as personalized model appeal for clients. In this paper, we first propose to treat incentivization and personalization as interrelated challenges and solve them with an incentive mechanism that fosters personalized learning. Additionally, current methods depend on an aggregator for client clustering, which is limited by a lack of access to clients' confidential information due to privacy constraints, leading to inaccurate clustering. To overcome this, we propose direct client involvement, allowing clients to indicate their cluster membership preferences based on data distribution and incentive-driven feedback. Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation. Our evaluation demonstrates significant improvements in test accuracy (8-45%), personalized model appeal (3-38%), and participation rates (31-100%) over existing FL models, including those addressing data heterogeneity and personalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_07514 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | IP-FL: Incentivized and Personalized Federated Learning Khan, Ahmad Faraz Wang, Xinran Le, Qi Abdeen, Zain ul Khan, Azal Ahmad Ali, Haider Jin, Ming Ding, Jie Butt, Ali R. Anwar, Ali Machine Learning Artificial Intelligence Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentives such as personalized model appeal for clients. In this paper, we first propose to treat incentivization and personalization as interrelated challenges and solve them with an incentive mechanism that fosters personalized learning. Additionally, current methods depend on an aggregator for client clustering, which is limited by a lack of access to clients' confidential information due to privacy constraints, leading to inaccurate clustering. To overcome this, we propose direct client involvement, allowing clients to indicate their cluster membership preferences based on data distribution and incentive-driven feedback. Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation. Our evaluation demonstrates significant improvements in test accuracy (8-45%), personalized model appeal (3-38%), and participation rates (31-100%) over existing FL models, including those addressing data heterogeneity and personalization. |
| title | IP-FL: Incentivized and Personalized Federated Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2304.07514 |