Search Results for author:
Found 2 papers, 1 papers with code
Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
We show how implicit GNN layers can be viewed as the fixed-point equation of a Dirichlet energy minimization problem and give conditions under which it may suffer from over-smoothing during training (OST) and inference (OSI).
Few-shot Learning by Focusing on Differences
Few-shot classification may involve differentiating data that belongs to a different level of labels granularity.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
