When Are Graph Neural Networks Better Than Structure-Agnostic Methods?

Onderzoeksoutput: Conference paperResearch


Graph neural networks (GNNs) are commonly applied to graph data, but their performance is often poorly understood. It is easy to find examples in which a GNN is unable to learn useful graph representations, but generally hard to explain why. In this work, we analyse the effectiveness of graph representations learned by shallow GNNs (2-layers) for input graphs with different structural properties and feature information. We expand on the failure cases by decoupling the impact of structural and feature information on the learning process. Our results indicate that GNNs' implicit architectural assumptions are tightly related to the structural properties of the input graph and may impair its learning ability. In case of mismatch, they can often be outperformed by structure-agnostic methods like multi-layer perceptron.
Originele taal-2English
TitelI Can't Believe It's Not Better Workshop: Understanding Deep Learning Through Empirical Falsification
Aantal pagina's10
StatusPublished - 2022
EvenementNeurIPS 2022 - The New Orleans Convention Center, New Orleans, United States
Duur: 28 nov 20229 dec 2022


ConferenceNeurIPS 2022
Land/RegioUnited States
StadNew Orleans
Internet adres


Duik in de onderzoeksthema's van 'When Are Graph Neural Networks Better Than Structure-Agnostic Methods?'. Samen vormen ze een unieke vingerafdruk.

Citeer dit