Interpolation-Prediction Networks for Irregularly Sampled Time Series

Authors: Satya Narayan Shukla, Benjamin Marlin

ICLR 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We investigate the performance of this architecture on both classification and regression tasks, showing that our approach outperforms a range of baseline and recently proposed models.
Researcher Affiliation Academia Satya Narayan Shukla College of Information and Computer Sciences University of Massachusetts Amherst snshukla@cs.umass.edu Benjamin M. Marlin College of Information and Computer Sciences University of Massachusetts Amherst marlin@cs.umass.edu
Pseudocode No The paper contains mathematical equations and architectural diagrams but no explicit 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes 1Our implementation is available at : https://github.com/mlds-lab/interp-net
Open Datasets Yes We test the model framework on two publicly available real-world datasets: MIMIC-III 3 a multivariate time series dataset consisting of sparse and irregularly sampled physiological signals collected at Beth Israel Deaconess Medical Center from 2001 to 2012 (Johnson et al., 2016), and UWave Gesture 4 a univariate time series data set consisting of simple gesture patterns divided into eight categories (Liu et al., 2009).
Dataset Splits Yes For MIMIC-III, we create our own dataset (appendix A.1) and report the results of a 5-fold cross validation experiment... and Out of the training data, 30% is used for validation.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions 'Tensor Flow' but does not specify its version number or any other software dependencies with version numbers.
Experiment Setup Yes We use cross-entropy loss for classification and squared error for regression. We also include ℓ2 regularizers for both the interpolation and prediction networks parameters. δI, δP , and δR are hyper-parameters that control the trade-off between the components of the objective function.