# Deep graph learning for semi-supervised classification

arXiv: https://arxiv.org/abs/2005.14403 · HTML: https://mlsanity.com/paper/2005.14403/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2020.

## Built on by (most cited first, 4 of 4)

- [GANN: Graph Alignment Neural Network for Semi-Supervised Learning](https://mlsanity.com/paper/2303.07778/) (2023)
- [Density-Aware Hyper-Graph Neural Networks for Graph-based Semi-supervised Node Classification](https://mlsanity.com/paper/2201.11511/) (2022)
- [Multi-view graph structure learning using subspace merging on Grassmann manifold](https://mlsanity.com/paper/2204.05258/) (2022)
- [DualHGNN: A Dual Hypergraph Neural Network for Semi-Supervised Node Classification based on Multi-View Learning and Density Awareness](https://mlsanity.com/paper/2306.04214/) (2023)

## Abstract (arXiv)

Graph learning (GL) can dynamically capture the distribution structure (graph structure) of data based on graph convolutional networks (GCN), and the learning quality of the graph structure directly influences GCN for semi-supervised classification. Existing methods mostly combine the computational layer and the related losses into GCN for exploring the global graph(measuring graph structure from all data samples) or local graph (measuring graph structure from local data samples). Global graph emphasises on the whole structure description of the inter-class data, while local graph trend to the neighborhood structure representation of intra-class data. However, it is difficult to simultaneously balance these graphs of the learning process for semi-supervised classification because of the interdependence of these graphs. To simulate the interdependence, deep graph learning(DGL) is proposed to find the better graph representation for semi-supervised classification. DGL can not only learn the global structure by the previous layer metric computation updating, but also mine the local structure by next layer local weight reassignment. Furthermore, DGL can fuse the different structures by dynamically encoding the interdependence of these structures, and deeply mine the relationship of the different structures by the hierarchical progressive learning for improving the performance of semi-supervised classification. Experiments demonstrate the DGL outperforms state-of-the-art methods on three benchmark datasets (Citeseer,Cora, and Pubmed) for citation networks and two benchmark datasets (MNIST and Cifar10) for images.