Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912190712250368 |
|---|---|
| author | Zheng, Liangwewi Nathan Zhang, Wei Emma Yue, Lin Xu, Miao Maennel, Olaf Chen, Weitong |
| author_facet | Zheng, Liangwewi Nathan Zhang, Wei Emma Yue, Lin Xu, Miao Maennel, Olaf Chen, Weitong |
| contents | Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stability and heavy trainable parameter. Furthermore, there is limited understanding of the behavior of the learned activation functions derived from B-splines. In this work, we analyze the behavior of KANs through the lens of spline knots and derive the lower and upper bound for the number of knots in B-spline-based KANs. To address existing limitations, we propose a novel Free Knots KAN that enhances the performance of the original KAN while reducing the number of trainable parameters to match the trainable parameter scale of standard Multi-Layer Perceptrons (MLPs). Additionally, we introduce new a training strategy to ensure $C^2$ continuity of the learnable spline, resulting in smoother activation compared to the original KAN and improve the training stability by range expansion. The proposed method is comprehensively evaluated on 8 datasets spanning various domains, including image, text, time series, multimodal, and function approximation tasks. The promising results demonstrates the feasibility of KAN-based network and the effectiveness of proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09283 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability Zheng, Liangwewi Nathan Zhang, Wei Emma Yue, Lin Xu, Miao Maennel, Olaf Chen, Weitong Machine Learning Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stability and heavy trainable parameter. Furthermore, there is limited understanding of the behavior of the learned activation functions derived from B-splines. In this work, we analyze the behavior of KANs through the lens of spline knots and derive the lower and upper bound for the number of knots in B-spline-based KANs. To address existing limitations, we propose a novel Free Knots KAN that enhances the performance of the original KAN while reducing the number of trainable parameters to match the trainable parameter scale of standard Multi-Layer Perceptrons (MLPs). Additionally, we introduce new a training strategy to ensure $C^2$ continuity of the learnable spline, resulting in smoother activation compared to the original KAN and improve the training stability by range expansion. The proposed method is comprehensively evaluated on 8 datasets spanning various domains, including image, text, time series, multimodal, and function approximation tasks. The promising results demonstrates the feasibility of KAN-based network and the effectiveness of proposed method. |
| title | Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.09283 |