Graph-Guided Network for Irregularly Sampled Multivariate Time Series

Xiang Zhang, Marko Zeman, Theodoros Tsiligkaridis, Marinka Zitnik
10/11/2021
cs.LGcs.AI

Official code: mims-harvard/Raindrop (228 stars, MIT, last commit 2022-10-04). 1 more implementation below.

Abstract

In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subsets of variables (sensors) observed at different time points. Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data. RAINDROP represents every sample as a separate sensor graph and models time-varying dependencies between sensors with a novel message passing operator. It estimates the latent sensor graph structure and leverages the structure together with nearby observations to predict misaligned readouts. This model can be interpreted as a graph neural network that sends messages over graphs that are optimized for capturing time-varying dependencies among sensors. We use RAINDROP to classify time series and interpret temporal dynamics on three healthcare and human activity datasets. RAINDROP outperforms state-of-the-art methods by up to 11.4% (absolute F1-score points), including techniques that deal with irregular sampling using fixed discretization and set functions. RAINDROP shows superiority in diverse setups, including challenging leave-sensor-out settings.

View on arXivView PDF

Code Implementations(2)

mims-harvard/RaindropOfficial100%
MIT

Graph Neural Networks for Irregular Time Series

22849Python, Jupyter NotebookJul 9, 20214 years agoMIT
deep-learningembeddingsgraph-neural-networksirregular-time-seriesmachine-learning+2 more
WenjieDu/PyPOTSCommunity100%
PyTorchBSD-3-Clause

A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

2,060190Shell, PythonMar 29, 20225 months agoBSD-3-Clause
anomaly-detectionclassificationclusteringdata-analysisdata-mining+10 more

Similar Papers

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

86% match1 repo8622023

Temporal Graph Neural Networks for Irregular Data

86% match1 repo212023

Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction

85% match1 repo2024

WaveGNN: Integrating Graph Neural Networks and Transformers for Decay-Aware Classification of Irregular Clinical Time-Series

85% match2024

Set Functions for Time Series

85% match1 repo1302019

Coupled Attention Networks for Multivariate Time Series Anomaly Detection

85% match2023

Cite this paper

@article{zhang2021graphguided,
  title  = {Graph-Guided Network for Irregularly Sampled Multivariate Time Series},
  author = {Xiang Zhang and Marko Zeman and Theodoros Tsiligkaridis and Marinka Zitnik},
  year   = {2021},
  eprint = {2110.05357},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2110.05357}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2110.05357.svg)](https://codeofpaper.com/paper/2110.05357)

Discussion