Coherence-based Label Propagation over Time Series for Accelerated Active Learning

2021-09-29 · ICLR 2022 4 · Yooju Shin, Susik Yoon, Sundong Kim, Hwanjun Song, Jae-Gil Lee, Byung Suk Lee

Time-series data are ubiquitous these days, but lack of the labels in time-series data is regarded as a hurdle for its broad applicability. Meanwhile, active learning has been successfully adopted to reduce the labeling efforts in various tasks. Thus, this paper addresses an important issue, time-series active learning. Inspired by the temporal coherence in time-series data, where consecutive data points tend to have the same label, our label propagation framework, called TCLP, automatically assigns a queried label to the data points within an accurately estimated time-series segment, thereby significantly boosting the impact of an individual query. Compared with traditional time-series active learning, TCLP is shown to improve the classification accuracy by up to 5.9 times when only 0.4% of data points in the entire time series are queried for their labels.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningTime SeriesTime Series Analysis

Spectral Propagation Graph Network for Few-shot Time Series Classification

2022-02-08 · Ling Yang, Shenda Hong, Luxia Zhang

Few-shot Time Series Classification (few-shot TSC) is a challenging problem in time series analysis. It is more difficult to classify when time series of the same class are not completely consistent in spectral domain or…

Classification Time Series Time Series Analysis Time Series Classification

On The Complexity of Sparse Label Propagation

2018-04-25 · Alexander Jung

This paper investigates the computational complexity of sparse label propagation which has been proposed recently for processing network structured data. Sparse label propagation amounts to a convex optimization problem …

Time Series Time Series Analysis

LLM-Enhanced Reinforcement Learning for Time Series Anomaly Detection

2026-01-05 · Bahareh Golchin, Banafsheh Rekabdar, Danielle Justo arxiv

Detecting anomalies in time series data is crucial for finance, healthcare, sensor networks, and industrial monitoring applications. However, time series anomaly detection often suffers from sparse labels, complex tempor…

Time Series Anomaly Detection Reinforcement Learning Active Learning

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

2023-09-21 · NeurIPS 2023 11

Deep Neural Networks (DNNs) have been criticized because they easily overfit noisy (incorrect) labels. To improve the robustness of DNNs, existing methods for image data regard samples with small training losses as corre…

Deep Learning-based Damage Mapping with InSAR Coherence Time Series

2021-05-24 · Oliver L. Stephenson, Tobias Köhne, Eric Zhan, Brent E. Cahill 외

Satellite remote sensing is playing an increasing role in the rapid mapping of damage after natural disasters. In particular, synthetic aperture radar (SAR) can image the Earth's surface and map damage in all weather con…

Deep Learning Time Series Time Series Analysis