One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912358931103744 |
|---|---|
| author | Luetto, Simone Garuti, Fabrizio Sangineto, Enver Forni, Lorenzo Cucchiara, Rita |
| author_facet | Luetto, Simone Garuti, Fabrizio Sangineto, Enver Forni, Lorenzo Cucchiara, Rita |
| contents | There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features are represented using a set of frequency functions and the whole network is uniformly trained with a unique loss function. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_06375 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data Luetto, Simone Garuti, Fabrizio Sangineto, Enver Forni, Lorenzo Cucchiara, Rita Machine Learning Artificial Intelligence There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features are represented using a set of frequency functions and the whole network is uniformly trained with a unique loss function. |
| title | One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2302.06375 |