Semi-Supervised Learning With Graph Learning-Convolutional Networks

By Bo Jiang, Ziyan Zhang, Doudou Lin, Jin Tang, Bin Luo. Computer Vision and Pattern Recognition, 2019

452 citations recorded by the source corpus.

Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may not be optimal for semi-supervised learning tasks. In this paper, we propose a novel Graph Learning-Convolutional Network (GLCN) for graph data representation and semi-supervised learning. The aim of GLCN is to learn an optimal graph structure that best serves graph CNNs for semi-supervised learning by integrating both graph learning and graph convolution in a unified network architecture. The main advantage is that in GLCN both given labels and the estimated labels are incorporated and thus can provide useful ‘weakly’ supervised information to refine (or learn) the graph construction and also to facilitate the graph convolution operation for unknown label estimation. Experimental results on seven benchmarks demonstrate that GLCN significantly outperforms the state-of-the-art traditional fixed structure based graph CNNs.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/960a6293d068e479435b693df04b839b24ffb7d9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chuan Shi
2. Xiao Wang
3. Massimiliano Mancini
4. Yao Ma
5. Binbin Hu
6. Yanfang Ye
7. Jiliang Tang
8. Suhang Wang

In Computer Vision and Pattern Recognition

1. Xiatian Zhu
2. Massimiliano Mancini
3. Junchi Yan
4. Yanbei Chen
5. Zeynep Akata
6. Yi Yang
7. David Paul Wipf
8. Xiao Wang

Citations in the corpus

• Reliable Data Distillation on Graph Convolutional Network (2020, methodology): “With an explicit graph-based regularization [29], the label information can be smoothed over the graph and the performances of GCN can be enhanced accordingly.”
• Graph Structure Learning for Robust Graph Neural Networks (2020, methodology): “Given the adjacency matrix A of a poisoned graph, we can formulate the above process as a structure learning problem [16, 27]:”
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification (2023, background): “02M GLCN [17] Function Fixed Not necessary Yes O(N(2)) 0.”
• Heterogeneous Graph Structure Learning for Graph Neural Networks (2021, background): “GLCN (Jiang et al. 2019) generates similarity-based graph structure from node features.”
• Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, methodology): “Graph-based regularization is later reformulated for semi-supervised learning with deep neural networks, such as EmbedNN [43], Graph Convolutional Network [78], [79], Teacher Graph [80], and Label Propagation [81].”
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings (2020, background): “Common options for metric learning include cosine similarity [41, 50], radial basis function (RBF) kernel [54, 32] and attention mechanisms [47, 22].”