Anisotropic Graph Convolutional Network for Semi-supervised Learning

by   Mahsa Mesgaran, et al.

Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification. However, these networks suffer from the issue of over-smoothing and shrinking effect of the graph due in large part to the fact that they diffuse features across the edges of the graph using a linear Laplacian flow. This limitation is especially problematic for the task of node classification, where the goal is to predict the label associated with a graph node. To address this issue, we propose an anisotropic graph convolutional network for semi-supervised node classification by introducing a nonlinear function that captures informative features from nodes, while preventing oversmoothing. The proposed framework is largely motivated by the good performance of anisotropic diffusion in image and geometry processing, and learns nonlinear representations based on local graph structure and node features. The effectiveness of our approach is demonstrated on three citation networks and two image datasets, achieving better or comparable classification accuracy results compared to the standard baseline methods.



There are no comments yet.


page 5

page 8

page 9

page 10


Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning

Recently, graph convolutional network (GCN) has been widely used for sem...

Graph Fairing Convolutional Networks for Anomaly Detection

Graph convolution is a fundamental building block for many deep neural n...

New GCNN-Based Architecture for Semi-Supervised Node Classification

The nodes of a graph existing in a specific cluster are more likely to c...

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

Data augmentation aims to generate new and synthetic features from the o...

A Graph Data Augmentation Strategy with Entropy Preserving

The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are...

Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks

In the modern age of social media and networks, graph representations of...

Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering

This paper presents FLGC, a simple yet effective fully linear graph conv...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.