F-KANs: Federated Kolmogorov-Arnold Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909381763792896 |
|---|---|
| author | Zeydan, Engin Vaca-Rubio, Cristian J. Blanco, Luis Pereira, Roberto Caus, Marius Aydeger, Abdullah |
| author_facet | Zeydan, Engin Vaca-Rubio, Cristian J. Blanco, Luis Pereira, Roberto Caus, Marius Aydeger, Abdullah |
| contents | In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to improve classification capabilities while preserving privacy. The study evaluates the performance of federated KANs (F- KANs) compared to traditional Multi-Layer Perceptrons (MLPs) on classification task. The results show that the F-KANs model significantly outperforms the federated MLP model in terms of accuracy, precision, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | F-KANs: Federated Kolmogorov-Arnold Networks Zeydan, Engin Vaca-Rubio, Cristian J. Blanco, Luis Pereira, Roberto Caus, Marius Aydeger, Abdullah Machine Learning Artificial Intelligence Cryptography and Security Networking and Internet Architecture In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to improve classification capabilities while preserving privacy. The study evaluates the performance of federated KANs (F- KANs) compared to traditional Multi-Layer Perceptrons (MLPs) on classification task. The results show that the F-KANs model significantly outperforms the federated MLP model in terms of accuracy, precision, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics. |
| title | F-KANs: Federated Kolmogorov-Arnold Networks |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Networking and Internet Architecture |
| url | https://arxiv.org/abs/2407.20100 |