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 a5b8701a0d Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.		4年前
docker	Start working on experiments/decagon_run.	4年前
docs	Add icosagon-reltype-rules.	4年前
experiments/decagon_run	Shuffle.	4年前
src	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	4年前
tests	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	4年前
.empty	Initial commit.	4年前
.gitignore	Add icosagon classes diagram.	4年前
README.md	Update README.md	4年前
requirements.txt	Start icosagon.	4年前

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.