Search Results for author:
Found 2 papers, 0 papers with code
Graph Laplacian for Semi-Supervised Learning
For semi-supervised problems, the common approach is to solve a constrained optimization problem, regularized by a Dirichlet energy, based on the graph-Laplacian.
BASiS: Batch Aligned Spectral Embedding Space
We analyze the degrees of freedom of learning this task using batches and propose a stable alignment mechanism that can work both with batch changes and with graph-metric changes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
