Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909901171720192 |
|---|---|
| author | Kim, Minkyu Choi, Hyun-Soo Kim, Jinho |
| author_facet | Kim, Minkyu Choi, Hyun-Soo Kim, Jinho |
| contents | Neural Additive Models (NAMs) have recently demonstrated promising predictive performance while maintaining interpretability. However, their capacity is limited to capturing only first-order feature interactions, which restricts their effectiveness on real-world datasets. To address this limitation, we propose Higher-order Neural Additive Models (HONAMs), an interpretable machine learning model that effectively and efficiently captures feature interactions of arbitrary orders. HONAMs improve predictive accuracy without compromising interpretability, an essential requirement in high-stakes applications. This advantage of HONAM can help analyze and extract high-order interactions present in datasets. The source code for HONAM is publicly available at https://github.com/gim4855744/HONAM/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_15409 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions Kim, Minkyu Choi, Hyun-Soo Kim, Jinho Machine Learning Neural Additive Models (NAMs) have recently demonstrated promising predictive performance while maintaining interpretability. However, their capacity is limited to capturing only first-order feature interactions, which restricts their effectiveness on real-world datasets. To address this limitation, we propose Higher-order Neural Additive Models (HONAMs), an interpretable machine learning model that effectively and efficiently captures feature interactions of arbitrary orders. HONAMs improve predictive accuracy without compromising interpretability, an essential requirement in high-stakes applications. This advantage of HONAM can help analyze and extract high-order interactions present in datasets. The source code for HONAM is publicly available at https://github.com/gim4855744/HONAM/. |
| title | Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2209.15409 |