Large Pre-trained time series models for cross-domain Time series analysis tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kamarthi, Harshavardhan, Prakash, B. Aditya
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913598253563904
author Kamarthi, Harshavardhan
Prakash, B. Aditya
author_facet Kamarthi, Harshavardhan
Prakash, B. Aditya
contents Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series analysis tasks usually involves designing and training a separate model from scratch leveraging training data and domain expertise specific to the task. We tackle a significant challenge for pre-training a foundational time-series model from multi-domain time-series datasets: extracting semantically useful tokenized inputs to the model across heterogenous time-series from different domains. We propose Large Pre-trained Time-series Models (LPTM) that introduces a novel method of adaptive segmentation that automatically identifies optimal dataset-specific segmentation strategy during pre-training. This enables LPTM to perform similar to or better than domain-specific state-of-art model when fine-tuned to different downstream time-series analysis tasks and under zero-shot settings. LPTM achieves superior forecasting and time-series classification results taking up to 40% less data and 50% less training time compared to state-of-art baselines. Code: www.github.com/AdityaLab/Samay
format Preprint
id arxiv_https___arxiv_org_abs_2311_11413
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Large Pre-trained time series models for cross-domain Time series analysis tasks
Kamarthi, Harshavardhan
Prakash, B. Aditya
Machine Learning
Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series analysis tasks usually involves designing and training a separate model from scratch leveraging training data and domain expertise specific to the task. We tackle a significant challenge for pre-training a foundational time-series model from multi-domain time-series datasets: extracting semantically useful tokenized inputs to the model across heterogenous time-series from different domains. We propose Large Pre-trained Time-series Models (LPTM) that introduces a novel method of adaptive segmentation that automatically identifies optimal dataset-specific segmentation strategy during pre-training. This enables LPTM to perform similar to or better than domain-specific state-of-art model when fine-tuned to different downstream time-series analysis tasks and under zero-shot settings. LPTM achieves superior forecasting and time-series classification results taking up to 40% less data and 50% less training time compared to state-of-art baselines. Code: www.github.com/AdityaLab/Samay
title Large Pre-trained time series models for cross-domain Time series analysis tasks
topic Machine Learning
url https://arxiv.org/abs/2311.11413