Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.17207 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929605755011072 |
|---|---|
| author | Thielmann, Anton Frederik Samiee, Soheila |
| author_facet | Thielmann, Anton Frederik Samiee, Soheila |
| contents | Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language model-based approaches, DL models for tabular data have also grown in complexity and size. Although tabular datasets do not typically pose scalability issues, the escalating size of these models has raised efficiency concerns. Despite its importance, efficiency has been relatively underexplored in tabular DL research. This paper critically examines the latest innovations in tabular DL, with a dual focus on performance and computational efficiency. The source code is available at https://github.com/basf/mamba-tabular. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17207 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning Thielmann, Anton Frederik Samiee, Soheila Machine Learning Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language model-based approaches, DL models for tabular data have also grown in complexity and size. Although tabular datasets do not typically pose scalability issues, the escalating size of these models has raised efficiency concerns. Despite its importance, efficiency has been relatively underexplored in tabular DL research. This paper critically examines the latest innovations in tabular DL, with a dual focus on performance and computational efficiency. The source code is available at https://github.com/basf/mamba-tabular. |
| title | On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.17207 |