Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

This repository holds the implementation for paper Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

Download our preprocessed UCI datasets to the data folder (created in the root path) via the following link

https://drive.google.com/drive/folders/1MlP5MiGeGNjb9GpWbI3HlUrpCFw2XqVA?usp=sharing

For Criteo and Avazu datasets, please download them from the Kaggle website.

To run the code, please refer to the bash script in each folder.

More information will be updated.

If you use the code or preprocessed datasets, please cite our paper:

@inproceedings{wu2021fate,
title = {Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach},
author = {Qitian Wu and Chenxiao Yang and Junchi Yan},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
year = {2021}
}