Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality

Authors: Saurabh Khanna, Vincent Y. F. Tan

ICLR 2020 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are carried out to demonstrate that the proposed economy-SRU based time series prediction model outperforms the MLP, LSTM and attention-gated CNN-based time series models considered previously for inferring Granger causality.
Researcher Affiliation Academia Saurabh Khanna Department of Electrical and Computer Engineering National University of Singapore EMAIL Vincent Y. F. Tan Department of Electrical and Computer Engineering Department of Mathematics National University of Singapore EMAIL
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code Yes Pytorch implementations of the proposed componentwise SRU and e SRU models are shared at https://github.com/sakhanna/SRU_for_GCI.
Open Datasets Yes For the BOLD signals: 'we use simulated BOLD time series measurements corresponding to the five different human subjects (labelled as 2 to 6) in the Sim-3.mat file shared at https://www.fmrib.ox.ac.uk/datasets/netsim/index.html.' For DREAM-3: 'DREAM-3 In Silico Network Inference Challenge (Prill et al. (2010); Marbach et al. (2009))'.
Dataset Splits Yes Two-fold crossvalidation across [5e-5, 1e-1]
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments.
Software Dependencies No The paper mentions 'Pytorch implementation' for the models but does not provide specific version numbers for Pytorch or other software dependencies.
Experiment Setup Yes Tables 7 to 11 summarize the chosen hyperparameters and configurations of the different NN/RNN models used for generating the results reported in Section 5.