GRAE
GRAE copied to clipboard
KevinMoonLab
Geometry Regularized Autoencoders (GRAE) for large-scale visualization and manifold learning
Running UMAP score method on train split before running on test split leads to obviously wrong test embeddings. (This was hot fixed for the paper by scoring test before train...
A lot of pairs have 0 distance, but aren't exactly equal. Need to remove duplicates given a small tolerance.
Metadata
Owner
Metadata
Geometry Regularized Autoencoders (GRAE) for large-scale visualization and manifold learning