Augmenting the FedProx Algorithm by Minimizing Convergence
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929369938657280 |
|---|---|
| author | Sarkar, Anomitra Vajpayee, Lavanya |
| author_facet | Sarkar, Anomitra Vajpayee, Lavanya |
| contents | The Internet of Things has experienced significant growth and has become an integral part of various industries. This expansion has given rise to the Industrial IoT initiative where industries are utilizing IoT technology to enhance communication and connectivity through innovative solutions such as data analytics and cloud computing. However this widespread adoption of IoT is demanding of algorithms that provide better efficiency for the same training environment without speed being a factor. In this paper we present a novel approach called G Federated Proximity. Building upon the existing FedProx technique our implementation introduces slight modifications to enhance its efficiency and effectiveness. By leveraging FTL our proposed system aims to improve the accuracy of model obtained after the training dataset with the help of normalization techniques such that it performs better on real time devices and heterogeneous networks Our results indicate a significant increase in the throughput of approximately 90% better convergence compared to existing model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Augmenting the FedProx Algorithm by Minimizing Convergence Sarkar, Anomitra Vajpayee, Lavanya Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing F.2.2; I.2.7 The Internet of Things has experienced significant growth and has become an integral part of various industries. This expansion has given rise to the Industrial IoT initiative where industries are utilizing IoT technology to enhance communication and connectivity through innovative solutions such as data analytics and cloud computing. However this widespread adoption of IoT is demanding of algorithms that provide better efficiency for the same training environment without speed being a factor. In this paper we present a novel approach called G Federated Proximity. Building upon the existing FedProx technique our implementation introduces slight modifications to enhance its efficiency and effectiveness. By leveraging FTL our proposed system aims to improve the accuracy of model obtained after the training dataset with the help of normalization techniques such that it performs better on real time devices and heterogeneous networks Our results indicate a significant increase in the throughput of approximately 90% better convergence compared to existing model performance. |
| title | Augmenting the FedProx Algorithm by Minimizing Convergence |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing F.2.2; I.2.7 |
| url | https://arxiv.org/abs/2406.00748 |