SeqNAS: Neural Architecture Search for Event Sequence Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910288286056448 |
|---|---|
| author | Udovichenko, Igor Shvetsov, Egor Divitsky, Denis Osin, Dmitry Trofimov, Ilya Glushenko, Anatoly Sukharev, Ivan Berestenev, Dmitry Burnaev, Evgeny |
| author_facet | Udovichenko, Igor Shvetsov, Egor Divitsky, Denis Osin, Dmitry Trofimov, Ilya Glushenko, Anatoly Sukharev, Ivan Berestenev, Dmitry Burnaev, Evgeny |
| contents | Neural Architecture Search (NAS) methods are widely used in various industries to obtain high quality taskspecific solutions with minimal human intervention. Event Sequences find widespread use in various industrial applications including churn prediction customer segmentation fraud detection and fault diagnosis among others. Such data consist of categorical and real-valued components with irregular timestamps. Despite the usefulness of NAS methods previous approaches only have been applied to other domains images texts or time series. Our work addresses this limitation by introducing a novel NAS algorithm SeqNAS specifically designed for event sequence classification. We develop a simple yet expressive search space that leverages commonly used building blocks for event sequence classification including multihead self attention convolutions and recurrent cells. To perform the search we adopt sequential Bayesian Optimization and utilize previously trained models as an ensemble of teachers to augment knowledge distillation. As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03246 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SeqNAS: Neural Architecture Search for Event Sequence Classification Udovichenko, Igor Shvetsov, Egor Divitsky, Denis Osin, Dmitry Trofimov, Ilya Glushenko, Anatoly Sukharev, Ivan Berestenev, Dmitry Burnaev, Evgeny Machine Learning Artificial Intelligence Neural Architecture Search (NAS) methods are widely used in various industries to obtain high quality taskspecific solutions with minimal human intervention. Event Sequences find widespread use in various industrial applications including churn prediction customer segmentation fraud detection and fault diagnosis among others. Such data consist of categorical and real-valued components with irregular timestamps. Despite the usefulness of NAS methods previous approaches only have been applied to other domains images texts or time series. Our work addresses this limitation by introducing a novel NAS algorithm SeqNAS specifically designed for event sequence classification. We develop a simple yet expressive search space that leverages commonly used building blocks for event sequence classification including multihead self attention convolutions and recurrent cells. To perform the search we adopt sequential Bayesian Optimization and utilize previously trained models as an ensemble of teachers to augment knowledge distillation. As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications. |
| title | SeqNAS: Neural Architecture Search for Event Sequence Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.03246 |