paper-with-me

Papers

Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution Selection

2025-02-14 · Kevin Garcia, Juan Manuel Perez, Yifeng Gao

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical contrastive learning models. Inspired by the fact that each resolution's data embedding is highly dependent, we introduce importance-aware resolution selection based training framework to reduce the computational cost. In the experiment, we demonstrate that the proposed method significantly improves training time while preserving the original model's integrity in extensive time series classification performance evaluations. Our code could be found here, https://github.com/KEEBVIN/IARS

📄 PDF Abstract BibTeX arXiv:2502.10567

Code (1)

keebvin/iars 공식 구현 pytorch

Tasks

Contrastive LearningSelf-Supervised LearningTime SeriesTime Series Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

2023-10-21 · NeurIPS 2023 11 · Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang

Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning method…

Contrastive LearningEEGRepresentation LearningTime Series+1

HCL-MTSAD: Hierarchical Contrastive Consistency Learning for Accurate Detection of Industrial Multivariate Time Series Anomalies

2024-04-12 · Haili Sun, Yan Huang, Lansheng Han, Cai Fu 외

Multivariate Time Series (MTS) anomaly detection focuses on pinpointing samples that diverge from standard operational patterns, which is crucial for ensuring the safety and security of industrial applications. The prima…

Anomaly DetectionContrastive LearningTime Series

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series

2022-12-02 · Qianwen Meng, Hangwei Qian, Yong liu, Lizhen Cui 외

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation lea…

ClusteringContrastive LearningRepresentation LearningTime Series+1

Self-Distilled Representation Learning for Time Series

2023-11-19 · Felix Pieper, Konstantin Ditschuneit, Martin Genzel, Alexandra Lindt 외

Self-supervised learning for time-series data holds potential similar to that recently unleashed in Natural Language Processing and Computer Vision. While most existing works in this area focus on contrastive learning, w…

Contrastive LearningRepresentation LearningSelf-Supervised LearningTime Series

CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection

2023-08-18 · Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu C. Aggarwal 외

One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios. Most of the existing anomaly detection methods focus on learning the normal behaviour of unlabelled tim…

Anomaly DetectionContrastive LearningRepresentation LearningTime Series+1