1 code implementation • 7 Aug 2023 • Guoji Fu, Mohammed Haroon Dupty, Yanfei Dong, Lee Wee Sun
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).
no code implementations • 25 Sep 2019 • Muhammad Rizki Maulana, Lee Wee Sun
Few-shot classification may involve differentiating data that belongs to a different level of labels granularity.