S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

ArXi:2604.19072v1 Announce Type: cross Semi-supervised learning with manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the key requirement is that the of the unknown marginal distribution has the geometric structure of a Riemannian manifold. Typically, the Laplace-Beltrami operator-based manifold regularization can be approximated empirically by the Laplacian regularization associated with the entire