Tripletformer for Probabilistic Interpolation of Irregularly sampled Time Series

TL;DR

The paper introduces Tripletformer, a novel attention-based encoder-decoder model for probabilistic interpolation of irregularly sampled time series with missing data, improving accuracy over existing methods.

Contribution

It presents a new set-based attention architecture specifically designed for irregular time series interpolation, outperforming baselines in accuracy and certainty.

Findings

Up to 32% reduction in negative loglikelihood error on real-world data.

Up to 85% reduction in error on synthetic datasets.

Effective handling of irregular sampling and missing values.

Abstract

Irregularly sampled time series data with missing values is observed in many fields like healthcare, astronomy, and climate science. Interpolation of these types of time series is crucial for tasks such as root cause analysis and medical diagnosis, as well as for smoothing out irregular or noisy data. To address this challenge, we present a novel encoder-decoder architecture called "Tripletformer" for probabilistic interpolation of irregularly sampled time series with missing values. This attention-based model operates on sets of observations, where each element is composed of a triple of time, channel, and value. The encoder and decoder of the Tripletformer are designed with attention layers and fully connected layers, enabling the model to effectively process the presented set elements. We evaluate the Tripletformer against a range of baselines on multiple real-world and synthetic datasets and show that it produces more accurate and certain interpolations. Results indicate an improvement in negative loglikelihood error by up to 32% on real-world datasets and 85% on synthetic datasets when using the Tripletformer compared to the next best model.