Geometrically Equivariant Graph Neural Networks: A Survey

02/15/2022
by   Jiaqi Han, et al.
0

Many scientific problems require to process data in the form of geometric graphs. Unlike generic graph data, geometric graphs exhibit symmetries of translations, rotations, and/or reflections. Researchers have leveraged such inductive bias and developed geometrically equivariant Graph Neural Networks (GNNs) to better characterize the geometry and topology of geometric graphs. Despite fruitful achievements, it still lacks a survey to depict how equivariant GNNs are progressed, which in turn hinders the further development of equivariant GNNs. To this end, based on the necessary but concise mathematical preliminaries, we analyze and classify existing methods into three groups regarding how the message passing and aggregation in GNNs are represented. We also summarize the benchmarks as well as the related datasets to facilitate later researches for methodology development and experimental evaluation. The prospect for future potential directions is also provided.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/29/2023

Graph Rewriting for Graph Neural Networks

Given graphs as input, Graph Neural Networks (GNNs) support the inferenc...
research
07/22/2021

Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks

Graph neural networks (GNNs) have achieved remarkable success as a frame...
research
06/20/2023

Uncertainty Estimation for Molecules: Desiderata and Methods

Graph Neural Networks (GNNs) are promising surrogates for quantum mechan...
research
06/07/2022

Utility of Equivariant Message Passing in Cortical Mesh Segmentation

The automated segmentation of cortical areas has been a long-standing ch...
research
05/12/2021

Graph Neural Networks for Inconsistent Cluster Detection in Incremental Entity Resolution

Online stores often utilize product relationships such as bundles and su...
research
06/01/2023

Renormalized Graph Neural Networks

Graph Neural Networks (GNNs) have become essential for studying complex ...
research
02/03/2022

Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networks

From designing architected materials to connecting mechanical behavior a...

Please sign up or login with your details

Forgot password? Click here to reset