ExGAN: Adversarial Generation of Extreme Samples

Authors: Siddharth Bhatia, Arjit Jain, Bryan Hooi6750-6758

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on real US precipitation data show that our method generates realistic samples, based on visual inspection and quantitative measures, in an efficient manner.
Researcher Affiliation Academia 1National University of Singapore 2IIT Bombay siddharth@comp.nus.edu.sg, arjit@cse.iitb.ac.in, bhooi@comp.nus.edu.sg
Pseudocode Yes Algorithm 1: Distribution Shifting; Algorithm 2: EVT-based Conditional Generation
Open Source Code Yes Reproducibility: Our code and datasets are publicly available at https://github.com/Stream-AD/Ex GAN.
Open Datasets Yes Reproducibility: Our code and datasets are publicly available at https://github.com/Stream-AD/Ex GAN.
Dataset Splits Yes We use the daily spatial rainfall distribution for the duration January 2010 to December 2016 as our training set, and for the duration of January 2017 to August 2020 as our test set.
Hardware Specification No The paper does not provide specific details about the hardware used for the experiments (e.g., GPU/CPU models, memory).
Software Dependencies Yes Our Ex GAN model is implemented in Python 3.6 using PyTorch 1.4.0.
Experiment Setup Yes Details about our experimental setup, network architecture and software implementation can be found in Appendix A, B and C respectively.