paper-with-me

Papers

Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

2023-12-27 · Hyowon Wi, Yehjin Shin, Noseong Park

Time series imputation is one of the most fundamental tasks for time series. Real-world time series datasets are frequently incomplete (or irregular with missing observations), in which case imputation is strongly required. Many different time series imputation methods have been proposed. Recent self-attention-based methods show the state-of-the-art imputation performance. However, it has been overlooked for a long time to design an imputation method based on continuous-time recurrent neural networks (RNNs), i.e., neural controlled differential equations (NCDEs). To this end, we redesign time series (variational) autoencoders based on NCDEs. Our method, called continuous-time autoencoder (CTA), encodes an input time series sample into a continuous hidden path (rather than a hidden vector) and decodes it to reconstruct and impute the input. In our experiments with 4 datasets and 19 baselines, our method shows the best imputation performance in almost all cases.

📄 PDF Abstract BibTeX arXiv:2312.16581

Code (0)

등록된 구현이 없습니다.

Tasks

ImputationIrregular Time SeriesTime Series

Similar Papers 제목 키워드 기반

Learning from Irregularly-Sampled Time Series: A Missing Data Perspective

2020-08-17 · ICML 2020 1 · Steven Cheng-Xian Li, Benjamin M. Marlin

Irregularly-sampled time series occur in many domains including healthcare. They can be challenging to model because they do not naturally yield a fixed-dimensional representation as required by many standard machine lea…

DecoderTime SeriesTime Series Analysis

Continuous-Time Linear Positional Embedding for Irregular Time Series Forecasting

2024-09-30 · Byunghyun Kim, Jae-Gil Lee

Irregularly sampled time series forecasting, characterized by non-uniform intervals, is prevalent in practical applications. However, previous research have been focused on regular time series forecasting, typically rely…

Irregular Time SeriesTime SeriesTime Series Forecasting

Neural Laplace Control for Continuous-time Delayed Systems

2023-02-24 · Samuel Holt, Alihan Hüyük, Zhaozhi Qian, Hao Sun 외

Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays. Such environments are characterized by two distinctive features: firstly, the state x(t) is observed at irreg…

Model Predictive ControlOffline RLReinforcement Learning (RL)

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

2024-02-16 · NeurIPS 2023 11 · Yuqi Chen, Kan Ren, Yansen Wang, Yuchen Fang 외

Modeling continuous-time dynamics on irregular time series is critical to account for data evolution and correlations that occur continuously. Traditional methods including recurrent neural networks or Transformer models…

Inductive BiasIrregular Time SeriesTime Series

Continuous Time Evidential Distributions for Irregular Time Series

2023-07-25 · Taylor W. Killian, Haoran Zhang, Thomas Hartvigsen, Ava P. Amini

Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from. It is difficult to infer the value of a feature at any given time when observations are spora…

Irregular Time SeriesTime SeriesTime Series Classification