paper-with-me

Papers

UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning

2023-03-24 · Zhiyu Liang, Chen Liang, Zheng Liang, Hongzhi Wang, Bo Zheng

Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To improve the performance and address the practical problems universally, we develop UniTS, a novel framework that incorporates self-supervised representation learning (or pre-training). The components of UniTS are designed using sklearn-like APIs to allow flexible extensions. We demonstrate how users can easily perform an analysis task using the user-friendly GUIs, and show the superior performance of UniTS over the traditional task-specific methods without self-supervised pre-training on five mainstream tasks and two practical settings.

📄 PDF Abstract BibTeX arXiv:2303.13804

Code (1)

lceomlet/units 공식 구현 pytorch

Tasks

Representation LearningTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

UniTS: A Unified Multi-Task Time Series Model

2024-02-29 · ShangHua Gao, Teddy Koker, Owen Queen, Thomas Hartvigsen 외

Although pre-trained transformers and reprogrammed text-based LLMs have shown strong performance on time series tasks, the best-performing architectures vary widely across tasks, with most models narrowly focused on spec…

Anomaly DetectionImputationmodelTime Series+1

Seamless Monitoring of Stress Levels Leveraging a Universal Model for Time Sequences

2024-07-04 · Davide Gabrielli, Bardh Prenkaj, Paola Velardi

Monitoring the stress level in patients with neurodegenerative diseases can help manage symptoms, improve patient's quality of life, and provide insight into disease progression. In the literature, ECG, actigraphy, speec…

Anomaly Detection

ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis

2024-03-03 · Mingyue Cheng, Jiqian Yang, Tingyue Pan, Qi Liu 외

Designing effective models for learning time series representations is foundational for time series analysis. Many previous works have explored time series representation modeling approaches and have made progress in thi…

Time SeriesTime Series AnalysisTime Series Forecasting

Memory makes computation universal, remember?

2024-12-23 · Erik Garrison

Recent breakthroughs in AI capability have been attributed to increasingly sophisticated architectures and alignment techniques, but a simpler principle may explain these advances: memory makes computation universal. Mem…

General Time-series Model for Universal Knowledge Representation of Multivariate Time-Series data

2025-02-05 · Cheng He, Xu Huang, Gangwei Jiang, Zhaoyi Li 외

Universal knowledge representation is a central problem for multivariate time series(MTS) foundation models and yet remains open. This paper investigates this problem from the first principle and it makes four folds of c…

Anomaly DetectionImputationTime SeriesTime Series Analysis