Topological based classification using graph convolutional networks

2019/10/26 by Roy Abel, Abel, Roy, Idan Benami +3 · 1 citation
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Social and Information Networks (cs.SI) #Topological and Geometric Data Analysis #Visual Attention and Saliency Detection

paper · pdf · doi:10.48550/arxiv.1911.06892

openalex publication_date 2019/10/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in general and specifically, Graph Convolutional Networks (GCN). First, we show that even in the absence of any external information on nodes, a good accuracy can be obtained on the prediction of the node class using either topological features, or using the neighbors class as an input to a GCN. This accuracy is slightly less than the one that can be obtained using content based GCN. Secondly, we show that explicitly adding the topology as an input to the GCN does not improve the accuracy when combined with external information on nodes. However, adding an additional adjacency matrix with edges between distant nodes with similar topology to the GCN does significantly improve its accuracy, leading to results better than all state of the art methods in multiple datasets.

Citations

• Deep Convolutional Networks on Graph-Structured Data
• Multidimensional Scaling by Optimizing Goodness of Fit to a Nonmetric Hypothesis
• A note on two problems in connexion with graphs
• Gated Graph Sequence Neural Networks
• Revisiting Semi-Supervised Learning with Graph Embeddings
• Semi-Supervised Classification with Graph Convolutional Networks
• N-GCN: Multi-scale Graph Convolution for Semi-supervised Node\n Classification
• Fast Interactive Object Annotation with Curve-GCN

Cited by

• Topological Regularization for Graph Neural Networks Augmentation

Related

• Topology and Prediction Focused Research on Graph Convolutional Neural Networks
• Expanding Label Sets for Graph Convolutional Networks
• Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification
• Demystifying Graph Convolution with a Simple Concatenation
• Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces