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!

Stanislaw Adaszewski 2cb561b1d4 Add test_prepare_relation_type_[01,02]().		il y a 4 ans
docs	Add icosagon-reltype-rules.	il y a 4 ans
src	Change test in test_unigram_03().	il y a 4 ans
tests	Add test_prepare_relation_type_[01,02]().	il y a 4 ans
.empty	Initial commit.	il y a 5 ans
.gitignore	Add icosagon classes diagram.	il y a 4 ans
README.md	Update README.md	il y a 5 ans
requirements.txt	Start icosagon.	il y a 4 ans

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

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