Skip to content

naganandy/G-MPNN-R

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

Conference

Source code for NeurIPS 2020 paper: Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

Model Usage:

  • Please use requirements.txt to install dependencies. To start training, run the following in GMPNN or MPNNR folder.

    python gmpnn.py --data WP-IND --agg max --log False
    python mpnnr.py --data cora --split 1 --log False
    
    • --data denotes the dataset to use
    • --log indicates whether to log results (and dump checkpoints for GMPNN)
    • --agg denotes the type of aggregation for GMPNN (max / mean / sum)
    • --split is the split number to use for MPNNR

Citation:

@incollection{gmpnnr_neurips20,
author = {Naganand Yadati},
title = {Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs},
booktitle = {Advances in Neural Information Processing Systems (NeurIPS) 33},
year = {2020},
publisher = {Curran Associates, Inc.}
}

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published