Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems
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_ | 1866917572647059456 |
|---|---|
| author | Hanjri, Mohammed El Reguieg, Hamza Attiaoui, Adil Abouaomar, Amine Kobbane, Abdellatif Kamili, Mohamed El |
| author_facet | Hanjri, Mohammed El Reguieg, Hamza Attiaoui, Adil Abouaomar, Amine Kobbane, Abdellatif Kamili, Mohamed El |
| contents | In the era of the Internet of Things (IoT), decentralized paradigms for machine learning are gaining prominence. In this paper, we introduce a federated learning model that capitalizes on the Euclidean distance between device model weights to assess their similarity and disparity. This is foundational for our system, directing the formation of coalitions among devices based on the closeness of their model weights. Furthermore, the concept of a barycenter, representing the average of model weights, helps in the aggregation of updates from multiple devices. We evaluate our approach using homogeneous and heterogeneous data distribution, comparing it against traditional federated learning averaging algorithm. Numerical results demonstrate its potential in offering structured, outperformed and communication-efficient model for IoT-based machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_12356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems Hanjri, Mohammed El Reguieg, Hamza Attiaoui, Adil Abouaomar, Amine Kobbane, Abdellatif Kamili, Mohamed El Machine Learning Distributed, Parallel, and Cluster Computing Computer Science and Game Theory In the era of the Internet of Things (IoT), decentralized paradigms for machine learning are gaining prominence. In this paper, we introduce a federated learning model that capitalizes on the Euclidean distance between device model weights to assess their similarity and disparity. This is foundational for our system, directing the formation of coalitions among devices based on the closeness of their model weights. Furthermore, the concept of a barycenter, representing the average of model weights, helps in the aggregation of updates from multiple devices. We evaluate our approach using homogeneous and heterogeneous data distribution, comparing it against traditional federated learning averaging algorithm. Numerical results demonstrate its potential in offering structured, outperformed and communication-efficient model for IoT-based machine learning. |
| title | Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Computer Science and Game Theory |
| url | https://arxiv.org/abs/2401.12356 |