Deep Manifold Learning with Graph Mining

TL;DR

This paper introduces a novel graph deep model with a non-gradient decision layer that unifies manifold learning and label local-structure preservation, achieving faster convergence and state-of-the-art results in graph mining tasks.

Contribution

It proposes a non-gradient decision layer with closed-form solutions for GCN, improving efficiency and performance in semi-supervised graph learning.

Findings

Achieves state-of-the-art performance on graph datasets.

Significantly accelerates convergence compared to traditional GCN.

Effectively captures topological information through manifold learning.

Abstract

Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc. However, softmax used as the decision layer in these frameworks is generally optimized with thousands of iterations via gradient descent. Furthermore, due to ignoring the inner distribution of the graph nodes, the decision layer might lead to an unsatisfactory performance in semi-supervised learning with less label support. To address the referred issues, we propose a novel graph deep model with a non-gradient decision layer for graph mining. Firstly, manifold learning is unified with label local-structure preservation to capture the topological information of the nodes. Moreover, owing to the non-gradient property, closed-form solutions is achieved to be employed as the decision layer for GCN. Particularly, a joint optimization method is designed for this graph model, which extremely accelerates the convergence of the model. Finally, extensive experiments show that the proposed model has achieved state-of-the-art performance compared to the current models.