Graph manifold learning with non-gradient decision layer

Ziheng Jiao, Hongyuan Zhang, Rui Zhang, Xuelong Li

Abstract: Highlights•Unifying the orthogonal manifold with label local-structure preservation to mine the topological information of the deep embeddings and make more accurate predictions, the novel non-gradient graph decision layer is put forward.•With the assistance of the designed theorems, the non-gradient graph decision layer can be solved with an elegant analytical solution theoretically.•By embedding the analytical solution into the gradient descent, a joint optimization strategy is designed to jointly optimize the graph convolution network and the proposed non-gradient decision layer.