User-friendly Foundation Model Adapters for Multivariate Time Series Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909319352549376 |
|---|---|
| author | Feofanov, Vasilii Ilbert, Romain Tiomoko, Malik Palpanas, Themis Redko, Ievgen |
| author_facet | Feofanov, Vasilii Ilbert, Romain Tiomoko, Malik Palpanas, Themis Redko, Ievgen |
| contents | Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dimensionality reduction techniques. Our goal is to enable users to run large pre-trained foundation models on standard GPUs without sacrificing performance. We investigate classical methods such as Principal Component Analysis alongside neural network-based adapters, aiming to reduce the dimensionality of multivariate time series data while preserving key features. Our experiments show up to a 10x speedup compared to the baseline model, without performance degradation, and enable up to 4.5x more datasets to fit on a single GPU, paving the way for more user-friendly and scalable foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12264 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | User-friendly Foundation Model Adapters for Multivariate Time Series Classification Feofanov, Vasilii Ilbert, Romain Tiomoko, Malik Palpanas, Themis Redko, Ievgen Machine Learning Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dimensionality reduction techniques. Our goal is to enable users to run large pre-trained foundation models on standard GPUs without sacrificing performance. We investigate classical methods such as Principal Component Analysis alongside neural network-based adapters, aiming to reduce the dimensionality of multivariate time series data while preserving key features. Our experiments show up to a 10x speedup compared to the baseline model, without performance degradation, and enable up to 4.5x more datasets to fit on a single GPU, paving the way for more user-friendly and scalable foundation models. |
| title | User-friendly Foundation Model Adapters for Multivariate Time Series Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.12264 |