Geometric Deep Learning: GNNs Beyond Permutation Equivariance

Показать описание

Casting graph neural networks (GNNs) within the Geometric Deep Learning blueprint, then demonstrating how we can use the blueprint to extend GNNs beyond the notion of permutation equivariance.
Guest Lecture at the Machine Learning with Graphs (CS224W) course, Stanford University, 30 November 2021

Petar Veličković

Рекомендации по теме

Комментарии

Very nice presentation. It is so informative, Peter.

Fetrose

Your explanation are really good!, Thank you!

vimukthirandika

Really good lecture about Geometric Deep Learning! Recently, my research paper applying GNN was questioned about the robustness of the model. This lecture gave me a lot of inspiration.

qiguosun

Thank you so much for sharing all your work! My honours thesis will be a thing thanks to ideas I got from watching your lectures!

nicolasgoulet

Extremely insightful! Thanks so much! Also agree that developing >1-WL GNNs using subgraphs and transfer learning (incl. pretraining) would be quite popular this year. Do you have any paper recommendations for latent graph inference?

yephuang

Geometric Deep Learning: GNNs Beyond Permutation Equivariance

Geometric Deep Learning: GNNs Beyond Permutation Equivariance

ICLR 2021 Keynote - 'Geometric Deep Learning: The Erlangen Programme of ML' - M Bronstein

GEOMETRIC DEEP LEARNING BLUEPRINT

Beyond the Patterns 28 - Petar Veličković - Geometric Deep Learning

Maria Bånkestad: Geometric deep learning with graph neural networks

IMVC 2020 Lecture - Geometric Deep Learning: Past, Present, and Future - Prof. Michael Bronstein

Petar Veličkovć - Geometric Deep Learning: Grids, Graphs, Groups, Geodesics and Gauges

Geometric Deep Learning (Part 1)

Geometric deep learning, from Euclid to drug design

Jens Agerberg: Teaching Neural Networks a Sense of Geometry

Geometric Deep Learning - Michael Bronstein - MLSS 2020, Tübingen

Geometric Deep Learning, Petar Veličković

How powerful are Graph Neural Networks? - Oxford Geometric Deep Learning

Geometric Deep Learning and Temporal Graph Networks

CIS COLLOQUIUM: Prof. Michael Bronstein - Geometric Deep Learning: from Euclid to drug design

LOGML 2021: Intro session + Michael Bronstein: Geometric Deep Learning: from Euclid to Drug Design

AMMI Course 'Geometric Deep Learning' - Lecture 1 (Introduction) - Michael Bronstein

IISc ECE Webinars: Geometric Deep Learning by M. Bronstein

Everything is Connected: Deep Learning on Graphs

AMMI Course 'Geometric Deep Learning' - Lecture 6 (Graphs & Sets II) - Petar Veličkovi...

AMMI 2022 Course 'Geometric Deep Learning' - Lecture 1 (Introduction) - Michael Bronstein

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

Geometric Deep Learning: Geordie Williamson

AMMI Course 'Geometric Deep Learning' - Lecture 12 (Applications & Conclusions) - Mich...