Skip to content

Latest commit

 

History

History
39 lines (30 loc) · 1001 Bytes

README.md

File metadata and controls

39 lines (30 loc) · 1001 Bytes

Rep the Set: Neural Networks for Learning Set Representations

Code for the paper Rep the Set: Neural Networks for Learning Set Representations.

Requirements

Code is written in Python 3.6 and requires:

  • lap 0.4.0
  • PyTorch 1.1
  • scikit-learn 0.21

Run the model

You can specify the dataset and the hyperparameters in the main.py files.

For the exact model, run:

python repset/main.py

For the approximate model, run:

python approxrepset/main.py

Cite

Please cite our paper if you use this code:

@inproceedings{skianis2020rep,
  title={Rep the Set: Neural Networks for Learning Set Representations},
  author={Skianis, Konstantinos and Nikolentzos, Giannis and Limnios, Stratis and Vazirgiannis, Michalis},
  booktitle={Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics},
  pages={1410--1420},
  year={2020}
}

Provided for academic use only