paper-with-me

홈 › Papers

Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask

2024-05-09 · Zineb Senane, Lele Cao, Valentin Leonhard Buchner, Yusuke Tashiro, Lei You, Pawel Herman, Mats Nordahl, Ruibo Tu, Vilhelm von Ehrenheim

Time Series Representation Learning (TSRL) focuses on generating informative representations for various Time Series (TS) modeling tasks. Traditional Self-Supervised Learning (SSL) methods in TSRL fall into four main categories: reconstructive, adversarial, contrastive, and predictive, each with a common challenge of sensitivity to noise and intricate data nuances. Recently, diffusion-based methods have shown advanced generative capabilities. However, they primarily target specific application scenarios like imputation and forecasting, leaving a gap in leveraging diffusion models for generic TSRL. Our work, Time Series Diffusion Embedding (TSDE), bridges this gap as the first diffusion-based SSL TSRL approach. TSDE segments TS data into observed and masked parts using an Imputation-Interpolation-Forecasting (IIF) mask. It applies a trainable embedding function, featuring dual-orthogonal Transformer encoders with a crossover mechanism, to the observed part. We train a reverse diffusion process conditioned on the embeddings, designed to predict noise added to the masked part. Extensive experiments demonstrate TSDE's superiority in imputation, interpolation, forecasting, anomaly detection, classification, and clustering. We also conduct an ablation study, present embedding visualizations, and compare inference speed, further substantiating TSDE's efficiency and validity in learning representations of TS data.

📄 PDF Abstract BibTeX arXiv:2405.05959

Code (2)

eqtpartners/tsde 공식 구현 pytorch
llcresearch/tsde 공식 구현 pytorch

Tasks

Anomaly DetectionImputationRepresentation LearningSelf-Supervised LearningTime Series

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
TS Spatio-temporal features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding. The workflow of the method is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting

2024-10-08 · Daoyu Wang, Mingyue Cheng, Zhiding Liu, Qi Liu 외

Self-supervised learning has become a popular and effective approach for enhancing time series forecasting, enabling models to learn universal representations from unlabeled data. However, effectively capturing both the …

DecoderDenoisingSelf-Supervised LearningTime Series+1

Series2Vec: Similarity-based Self-supervised Representation Learning for Time Series Classification

2023-12-07 · Navid Mohammadi Foumani, Chang Wei Tan, Geoffrey I. Webb, Hamid Rezatofighi 외

We argue that time series analysis is fundamentally different in nature to either vision or natural language processing with respect to the forms of meaningful self-supervised learning tasks that can be defined. Motivate…

Data AugmentationRepresentation LearningSelf-Supervised LearningTime Series+2

DiffStyleTS: Diffusion Model for Style Transfer in Time Series

2025-10-13 · Mayank Nagda, Phil Ostheimer, Justus Arweiler, Indra Jungjohann 외 arxiv

Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning models generalize in data-scarce domains. …

Anomaly DetectionData AugmentationStyle Transfer

TS-Diffusion: Generating Highly Complex Time Series with Diffusion Models

2023-11-06 · Yangming Li

While current generative models have achieved promising performances in time-series synthesis, they either make strong assumptions on the data format (e.g., regularities) or rely on pre-processing approaches (e.g., inter…

DecoderMissing ValuesTime Series

Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning

2020-11-27 · Haoyi Fan, Fengbin Zhang, Yue Gao

Self-supervised learning achieves superior performance in many domains by extracting useful representations from the unlabeled data. However, most of traditional self-supervised methods mainly focus on exploring the inte…

RelationRelational ReasoningRepresentation LearningSelf-Supervised Learning+3