Manifold-based multi-graph embedding for semi-supervised classification

Cong Hu

doi:10.1016/j.patrec.2024.04.003

Manifold-based multi-graph embedding for semi-supervised classification

2024-06-01

0

PRE

AI

DOI：10.1016/j.patrec.2024.04.003

Original

Original request for help

Save

Abstract

En 中文

Graph semi-supervised learning (GSSL) plays an important role in semi-supervised classification by leveraging the similarity of graph topology and convex optimization with Laplacian-based regularization. Current approaches mainly focus on data representation in the Euclidean space and solely rely on a single graph structure, ignoring the underlined manifold-valued structure of the data. To this end, we propose a novel manifold-based multi-graph embedding (M2GE), which explicitly learns representations on both Riemannian manifold and Euclidean space in the embedding learning process. Incorporating multi-graph structure, the rich and varied features are used by M2GE to more fully capture categorical information, where the heterogeneous spatial representations from manifold are complementary. Extensive experimental results on three popular benchmarks verify demonstrate the superiority of our method over state-of-the art competitors.

Keywords:

Semi-supervised learning

manifold learning

data augmentation

label propagation

deep neural network

Manifold-based multi-graph embedding for semi-supervised classification

Abstract

Journal

Organization