LGIRDec 27, 2023

Continuous-time Autoencoders for Regular and Irregular Time Series Imputation

arXiv:2312.16581v312 citationsh-index: 10WSDM
Originality Highly original
AI Analysis

This addresses the need for accurate imputation in incomplete real-world time series data, offering a novel approach that improves upon existing methods.

The paper tackled the problem of imputing missing values in regular and irregular time series by proposing a continuous-time autoencoder based on neural controlled differential equations, achieving state-of-the-art performance in almost all cases across 4 datasets and 19 baselines.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes