Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Authors: Zijie Huang, Yizhou Sun, Wei Wang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on motion capture, spring system, and charged particle datasets demonstrate the effectiveness of our approach.
Researcher Affiliation Academia Zijie Huang Department of Computer Science University of California, Los Angeles zijiehuang@cs.ucla.edu Yizhou Sun Department of Computer Science University of California, Los Angeles yzsun@cs.ucla.edu Wei Wang Department of Computer Science University of California, Los Angeles weiwang@cs.ucla.edu
Pseudocode No The paper describes methods through text and mathematical equations (e.g., Eqn 1, 2, 3, 4, 6, 7, 8) but does not include any clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes Our implementation is available online1. 1https://github.com/Zijie H/LG-ODE.git
Open Datasets Yes We illustrate the performance of our model on three different datasets: particles connected by springs, charged particles ( Kipf et al. [2]) and motion capture data ( CMU [16]).
Dataset Splits No The paper specifies training and testing sample counts ('20k training samples and 5k testing samples') and how walking trials are split into 'non-overlapping training (15 trials) and test sets (7 trials)', but does not explicitly mention or quantify a separate validation split with percentages or counts.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions general software components like 'neural ODE' and 'GNN', but does not provide specific software names with version numbers (e.g., Python 3.x, PyTorch 1.x) that are needed to replicate the experiment.
Experiment Setup No The paper mentions some experimental setup details, such as rescaling the time range to [0, 1] and using different observation percentages (40%, 60%, 80%), and describes the data splitting for interpolation and extrapolation tasks. However, it does not provide specific hyperparameters like learning rate, batch size, number of epochs, or optimizer settings within the main text.