Mixed-curvature graph representation learning for biological pathways. Most files are derived from and retain the commit history of this repository that provides hyperbolic embedding implementations of Representation Tradeoffs for Hyperbolic Embeddings + product embedding implementations of Learning Mixed-Curvature Representations in Product Spaces
The biological pathway analyses are presented in this workshop extended abstract:
Mixed-Curvature Representation Learning for Biological Pathway Graphs
Daniel McNeela, Frederic Sala+, Anthony Gitter+.
2023 ICML Workshop on Computational Biology.
+ Equal contribution
python pytorch/pytorch_hyperbolic.py learn --help to see options. Optimizer requires torch >=0.4.1. Example usage:
python pytorch/pytorch_hyperbolic.py learn data/edges/phylo_tree.edges --batch-size 64 --dim 10 -l 5.0 --epochs 100 --checkpoint-freq 10 --subsample 16
Products of hyperbolic spaces with Euclidean and spherical spaces are also supported. E.g. adding flags -euc 1 -edim 20 -sph 2 -sdim 10 embeds into a product of Euclidean space of dimension 20 with two copies of spherical space of dimension 10.
The code is available under the Apache License 2.0. Most of the source code is derived from the unlicensed hyperbolics repository, and the contributors to that repository have been added to the license copyright.