Search Results for author:
Found 2 papers, 0 papers with code
AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inference
More importantly, our interpretability framework provides a general approach for quantitatively comparing embedding spaces across different tasks based on their contributions, a dimension that has been overlooked in previous literature on latent graph inference.
Notes on Low-rank Matrix Factorization
The key idea of MF is that there exists latent structures in the data, by uncovering which we could obtain a compressed representation of the data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
