Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature

11/28/2022
by   Khang Nguyen, et al.
0

Graph Neural Networks (GNNs) had been demonstrated to be inherently susceptible to the problems of over-smoothing and over-squashing. These issues prohibit the ability of GNNs to model complex graph interactions by limiting their effectiveness at taking into account distant information. Our study reveals the key connection between the local graph geometry and the occurrence of both of these issues, thereby providing a unified framework for studying them at a local scale using the Ollivier's Ricci curvature. Based on our theory, a number of principled methods are proposed to alleviate the over-smoothing and over-squashing issues.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2022

Understanding the Relationship between Over-smoothing and Over-squashing in Graph Neural Networks

Graph Neural Networks (GNNs) have been successfully applied in many appl...
research
08/31/2023

Curvature-based Pooling within Graph Neural Networks

Over-squashing and over-smoothing are two critical issues, that limit th...
research
06/07/2020

Bayesian Graph Neural Networks with Adaptive Connection Sampling

We propose a unified framework for adaptive connection sampling in graph...
research
09/17/2023

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature

While Graph Neural Networks (GNNs) have been successfully leveraged for ...
research
07/28/2016

Incremental Noising and its Fractal Behavior

This manuscript is about further elucidating the concept of noising. The...
research
01/28/2021

Interpreting and Unifying Graph Neural Networks with An Optimization Framework

Graph Neural Networks (GNNs) have received considerable attention on gra...
research
06/15/2022

DiffWire: Inductive Graph Rewiring via the Lovász Bound

Graph Neural Networks (GNNs) have been shown to achieve competitive resu...

Please sign up or login with your details

Forgot password? Click here to reset