Graph Neural Networks with Heterophily

09/28/2020
by   Jiong Zhu, et al.
30

Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, most existing GNN models have an implicit assumption of homophily among the nodes connected in the graph, and therefore have largely overlooked the important setting of heterophily. In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily. The proposed framework incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in the graph, which can be learned in an end-to-end fashion, enabling it to go beyond the assumption of strong homophily. Theoretically, we show that replacing the compatibility matrix in our framework with the identity (which represents pure homophily) reduces to GCN. Our extensive experiments demonstrate the effectiveness of our approach in more realistic and challenging experimental settings with significantly less training data compared to previous works: CPGNN variants achieve state-of-the-art results in heterophily settings with or without contextual node features, while maintaining comparable performance in homophily settings.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 8

page 9

page 10

research
06/23/2021

Learnt Sparsification for Interpretable Graph Neural Networks

Graph neural networks (GNNs) have achieved great success on various task...
research
10/07/2019

Dynamic Self-training Framework for Graph Convolutional Networks

Graph neural networks (GNN) such as GCN, GAT, MoNet have achieved state-...
research
06/17/2022

Sheaf Neural Networks with Connection Laplacians

A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) tha...
research
06/09/2020

On the Bottleneck of Graph Neural Networks and its Practical Implications

Graph neural networks (GNNs) were shown to effectively learn from highly...
research
09/11/2020

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

Graph neural networks (GNNs) have been shown with superior performance i...
research
11/19/2021

Positional Encoder Graph Neural Networks for Geographic Data

Graph neural networks (GNNs) provide a powerful and scalable solution fo...
research
06/12/2020

Effective Training Strategies for Deep Graph Neural Networks

Graph Neural Networks (GNNs) tend to suffer performance degradation as m...

Please sign up or login with your details

Forgot password? Click here to reset