BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network

by   Zhixian Chen, et al.

Graph convolutional networks have achieved great success on graph-structured data. Many graph convolutional networks can be regarded as low-pass filters for graph signals. In this paper, we propose a new model, BiGCN, which represents a graph neural network as a bi-directional low-pass filter. Specifically, we not only consider the original graph structure information but also the latent correlation between features, thus BiGCN can filter the signals along with both the original graph and a latent feature-connection graph. Our model outperforms previous graph neural networks in the tasks of node classification and link prediction on most of the benchmark datasets, especially when we add noise to the node features.


page 1

page 2

page 3

page 4


Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering

Graph convolutional networks are becoming indispensable for deep learnin...

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

Graph neural networks have become one of the most important techniques t...

On the Information Theoretic Distance Measures and Bidirectional Helmholtz Machines

By establishing a connection between bi-directional Helmholtz machines a...

Dirichlet Graph Variational Autoencoder

Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have be...

Freshness or Accuracy, Why Not Both? Addressing Delayed Feedback via Dynamic Graph Neural Networks

The delayed feedback problem is one of the most pressing challenges in p...

Fisher-Bures Adversary Graph Convolutional Networks

In a graph convolutional network, we assume that the graph G is generate...

Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss

Graph convolutional networks (GCNs) and their variants have achieved gre...

Please sign up or login with your details

Forgot password? Click here to reset