mlsanityData to 14 Oct 2026

Temporal Dynamic Embedding for Irregularly Sampled Time Series

arXiv 2504.05768 ↗First posted 8 Apr 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In several practical applications, particularly healthcare, clinical data of each patient is individually recorded in a database at irregular intervals as required. This causes a sparse and irregularly sampled time series, which makes it difficult to handle as a structured representation of the prerequisites of neural network models. We therefore propose temporal dynamic embedding (TDE), which enables neural network models to receive data that change the number of variables over time. TDE regards each time series variable as an embedding vector evolving over time, instead of a conventional fixed structured representation, which causes a critical missing problem. For each time step, TDE allows for the selective adoption and aggregation of only observed variable subsets and represents the current status of patient based on current observations. The experiment was conducted on three clinical datasets: PhysioNet 2012, MIMIC-III, and PhysioNet 2019. The TDE model performed competitively or better than the imputation-based baseline and several recent state-of-the-art methods with reduced training runtime.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

19 of 42 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2018Deep learning for time series classification: a reviewcited by 576
  5. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  6. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  7. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  8. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 333
  9. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  10. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  11. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  12. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
7 more
  1. 2016GRAM: Graph-based Attention Model for Healthcare Representation Learningcited by 156
  2. 2019Set Functions for Time Seriescited by 138
  3. 2019Interpolation-Prediction Networks for Irregularly Sampled Time Seriescited by 89
  4. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  5. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
  6. 2016Multi-layer Representation Learning for Medical Conceptscited by 69
  7. 2019Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networkscited by 16

Built on by

Not cited yet.