IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an email to s dot adaszewski at gmail dot com. User accounts are meant only to report issues and/or generate pull requests. This is a purpose-specific Git hosting for ADARED projects. Thank you for your understanding!
Вы не можете выбрать более 25 тем Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
Stanislaw Adaszewski 706ff0b009 New implementation of normalize for one/two node types and sparse/dense - good. 4 лет назад
docs Work on icosagon.trainprep. 4 лет назад
src New implementation of normalize for one/two node types and sparse/dense - good. 4 лет назад
tests New implementation of normalize for one/two node types and sparse/dense - good. 4 лет назад
.empty Initial commit. 4 лет назад
.gitignore Started implementing convolutions, with tests. 4 лет назад
README.md Update README.md 4 лет назад
requirements.txt Start icosagon. 4 лет назад

README.md

decagon-pytorch

Introduction

Decagon is a method for learning node embeddings in multimodal graphs, and is especially useful for link prediction in highly multi-relational settings.

Decagon-PyTorch is a PyTorch reimplementation of the algorithm.

References

  1. Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks Bioinformatics, 34(13), i457-i466.