New Benchmarks for Learning on Non-Homophilous Graphs

04/03/2021
by   Derek Lim, et al.
0

Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute. As such, ubiquitous datasets for graph machine learning tasks have generally been highly homophilous, rewarding methods that leverage homophily as an inductive bias. Recent work has pointed out this particular focus, as new non-homophilous datasets have been introduced and graph representation learning models better suited for low-homophily settings have been developed. However, these datasets are small and poorly suited to truly testing the effectiveness of new methods in non-homophilous settings. We present a series of improved graph datasets with node label relationships that do not satisfy the homophily principle. Along with this, we introduce a new measure of the presence or absence of homophily that is better suited than existing measures in different regimes. We benchmark a range of simple methods and graph neural networks across our proposed datasets, drawing new insights for further research. Data and codes can be found at https://github.com/CUAI/Non-Homophily-Benchmarks.

READ FULL TEXT

page 8

page 10

research
10/27/2021

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Many widely used datasets for graph machine learning tasks have generall...
research
08/01/2019

Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview

Graph neural networks denote a group of neural network models introduced...
research
11/08/2018

A simple yet effective baseline for non-attribute graph classification

Graphs are complex objects that do not lend themselves easily to typical...
research
05/31/2022

Graph-level Neural Networks: Current Progress and Future Directions

Graph-structured data consisting of objects (i.e., nodes) and relationsh...
research
04/06/2023

Inductive Graph Unlearning

As a way to implement the "right to be forgotten" in machine learning, m...
research
07/09/2023

Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning

Graph-based methods have been extensively applied to whole-slide histopa...
research
11/28/2022

Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings

Asymmetrical distance structures (quasimetrics) are ubiquitous in our li...

Please sign up or login with your details

Forgot password? Click here to reset