Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces

11/01/2022
by   Ashish Tiwari, et al.
0

Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the homophily assumption and have shown limited performance on the heterophilous graphs. While several methods have been developed with new architectures to address heterophily, we argue that by learning graph representations across two spaces i.e., topology and feature space GCNs can address heterophily. In this work, we experimentally demonstrate the performance of the proposed GCN framework over semi-supervised node classification task on both homophilous and heterophilous graph benchmarks by learning and combining representations across the topological and the feature spaces.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/25/2020

Co-embedding of Nodes and Edges with Graph Neural Networks

Graph, as an important data representation, is ubiquitous in many real w...
research
08/10/2021

Self-supervised Consensus Representation Learning for Attributed Graph

Attempting to fully exploit the rich information of topological structur...
research
09/11/2020

CatGCN: Graph Convolutional Networks with Categorical Node Features

Recent studies on Graph Convolutional Networks (GCNs) reveal that the in...
research
06/11/2021

Is Homophily a Necessity for Graph Neural Networks?

Graph neural networks (GNNs) have shown great prowess in learning repres...
research
11/26/2018

HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition

Strong regulations in the financial industry mean that any decisions bas...
research
11/14/2020

Representing Deep Neural Networks Latent Space Geometries with Graphs

Deep Learning (DL) has attracted a lot of attention for its ability to r...
research
01/24/2022

Learning Graph Augmentations to Learn Graph Representations

Devising augmentations for graph contrastive learning is challenging due...

Please sign up or login with your details

Forgot password? Click here to reset