GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily

10/29/2021
by   Lun Du, et al.
0

Graph Neural Networks (GNNs) are widely used on a variety of graph-based machine learning tasks. For node-level tasks, GNNs have strong power to model the homophily property of graphs (i.e., connected nodes are more similar) while their ability to capture heterophily property is often doubtful. This is partially caused by the design of the feature transformation with the same kernel for the nodes in the same hop and the followed aggregation operator. One kernel cannot model the similarity and the dissimilarity (i.e., the positive and negative correlation) between node features simultaneously even though we use attention mechanisms like Graph Attention Network (GAT), since the weight calculated by attention is always a positive value. In this paper, we propose a novel GNN model based on a bi-kernel feature transformation and a selection gate. Two kernels capture homophily and heterophily information respectively, and the gate is introduced to select which kernel we should use for the given node pairs. We conduct extensive experiments on various datasets with different homophily-heterophily properties. The experimental results show consistent and significant improvements against state-of-the-art GNN methods.

READ FULL TEXT
research
05/11/2022

NDGGNET-A Node Independent Gate based Graph Neural Networks

Graph Neural Networks (GNNs) is an architecture for structural data, and...
research
10/23/2019

Feature Selection and Extraction for Graph Neural Networks

Graph Neural Networks (GNNs) have been a latest hot research topic in da...
research
11/03/2020

GAIN: Graph Attention Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs

Graph Neural Networks (GNNs) have led to state-of-the-art performance on...
research
05/16/2020

Graph Neural Networks with Composite Kernels

Learning on graph structured data has drawn increasing interest in recen...
research
02/07/2023

Heterophily-Aware Graph Attention Network

Graph Neural Networks (GNNs) have shown remarkable success in graph repr...
research
07/16/2021

Graph Kernel Attention Transformers

We introduce a new class of graph neural networks (GNNs), by combining s...
research
03/02/2021

Graph Information Vanishing Phenomenon inImplicit Graph Neural Networks

One of the key problems of GNNs is how to describe the importance of nei...

Please sign up or login with your details

Forgot password? Click here to reset