Anisotropic Graph Convolutional Network for Semi-supervised Learning

10/20/2020
by   Mahsa Mesgaran, et al.
0

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.

READ FULL TEXT

page 5

page 8

page 9

page 10

research
09/26/2018

Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning

Recently, graph convolutional network (GCN) has been widely used for sem...
research
10/20/2020

Graph Fairing Convolutional Networks for Anomaly Detection

Graph convolution is a fundamental building block for many deep neural n...
research
09/29/2020

New GCNN-Based Architecture for Semi-Supervised Node Classification

The nodes of a graph existing in a specific cluster are more likely to c...
research
06/16/2021

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

Data augmentation aims to generate new and synthetic features from the o...
research
07/13/2021

A Graph Data Augmentation Strategy with Entropy Preserving

The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are...
research
12/14/2021

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

In the modern age of social media and networks, graph representations of...
research
09/04/2020

LFGCN: Levitating over Graphs with Levy Flights

Due to high utility in many applications, from social networks to blockc...

Please sign up or login with your details

Forgot password? Click here to reset