Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.00420 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910769028792320 |
|---|---|
| author | Yu, Fangchen Hu, Ruilizhen Lin, Yidong Ma, Yuqi Huang, Zhenghao Li, Wenye |
| author_facet | Yu, Fangchen Hu, Ruilizhen Lin, Yidong Ma, Yuqi Huang, Zhenghao Li, Wenye |
| contents | The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demonstrate that KAE improves latent representation quality, reduces reconstruction errors, and achieves superior performance in downstream tasks such as retrieval, classification, and denoising, compared to standard autoencoders and other KAN variants. These results suggest KAE's potential as a useful tool for representation learning. Our code is available at \url{https://github.com/SciYu/KAE/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00420 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning Yu, Fangchen Hu, Ruilizhen Lin, Yidong Ma, Yuqi Huang, Zhenghao Li, Wenye Machine Learning The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demonstrate that KAE improves latent representation quality, reduces reconstruction errors, and achieves superior performance in downstream tasks such as retrieval, classification, and denoising, compared to standard autoencoders and other KAN variants. These results suggest KAE's potential as a useful tool for representation learning. Our code is available at \url{https://github.com/SciYu/KAE/}. |
| title | KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.00420 |