Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data
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_ | 1866916433785520128 |
|---|---|
| author | Sasse, Arthur Mendonça de Farias, Claudio Miceli |
| author_facet | Sasse, Arthur Mendonça de Farias, Claudio Miceli |
| contents | Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08961 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data Sasse, Arthur Mendonça de Farias, Claudio Miceli Machine Learning Artificial Intelligence Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing time. |
| title | Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.08961 |