The three folders contrain the code for training and evaluating GIL, GIL-D and GIL-H on three datasets (MIMIC-III, 35% missing Ophthalmic and 90% missing MNIST) used in the paper respectively. 

Environmental requirements:
Python 2.7
tensorflow 1.15.0
scikit-learn 0.24.0
pandas 0.24.2
numpy 1.16.6
scipy 1.2.1

Each folder is self-contained and has a seperate readme file introducing how to train, evaluate and load pre-trained checkpoints.

****************************************************************************************************
----------------------------------------------------------------------------------------------------
Due to the size limitation of the supplementary files that can be uploaded to OpenReview.net, we do not provide the data and pre-trained checkpoints here. Please download the full version (1.1GB) from https://drive.google.com/file/d/1cUjWb_AqYHnJG10M3bkEnfokOPcNsc7j/view?usp=sharing to access the data and pre-trained models.
----------------------------------------------------------------------------------------------------
****************************************************************************************************