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!
No puede seleccionar más de 25 temas Los temas deben comenzar con una letra o número, pueden incluir guiones ('-') y pueden tener hasta 35 caracteres de largo.
Stanislaw Adaszewski 52be4061b3 Adjust DecagonLayer to normalize per edge type. hace 4 años
docs Better way to compute DecagonLayer. hace 4 años
src/decagon_pytorch Adjust DecagonLayer to normalize per edge type. hace 4 años
tests/decagon_pytorch Adjust DecagonLayer to normalize per edge type. hace 4 años
.empty Initial commit. hace 4 años
.gitignore Started implementing convolutions, with tests. hace 4 años
README.md Update README.md hace 4 años

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.