Inducing Clusters Deep Kernel Gaussian Process for Longitudinal Data

Authors: Junjie Liang, Weijieying Ren, Hanifi Sahar, Vasant Honavar

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We describe the results of extensive experiments demonstrating that ICDKGP substantially outperforms the state-of-the-art longitudinal methods on data with both smoothly and non-smoothly varying outcomes.
Researcher Affiliation Academia Junjie Liang, Weijieying Ren, Hanifi Sahar, Vasant Honavar The Pennsylvania State University jliang282@outlook.com, {wjr5337, szh6071, vuh14}@psu.edu
Pseudocode No The paper describes its model and mathematical formulations but does not include any pseudocode or algorithm blocks.
Open Source Code No Full implementation details and the Appendix can be accessed through https://github.com/junjieliang672/ICDKGP/blob/main/ICDKGP-AAAI24 appendix.pdf. This link points to a PDF appendix, not directly to the source code repository.
Open Datasets Yes We used three real-world longitudinal data sets, each with some degree of discontinuities. (i) The SWAN (Sutton-Tyrrell et al. 2005) data is taken from a longitudinal study of women s health in midlife. (ii) GSS (Smith et al. 2015) data is taken from a 30-year longitudinal study... (iii) TADPOLE (Marinescu et al. 2018) data is taken from the Alzheimer s Disease Neuroimaging Initiative (ADNI) longitudinal study...
Dataset Splits Yes We evaluated the performance of each model on each regression task using 10 independent runs, using 50%, 20%, and 30% of data for training, validation, and testing respectively.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, processor types, or memory used for running the experiments.
Software Dependencies No The paper refers to implementation details in an appendix, but does not specify software dependencies with version numbers (e.g., Python version, library versions) in the main text.
Experiment Setup No The paper states that 'Full implementation details and the Appendix can be accessed through https://github.com/junjieliang672/ICDKGP/blob/main/ICDKGP-AAAI24 appendix.pdf,' implying hyperparameter and setup details are there, but they are not explicitly provided within the main body of the paper.