List: Geometric Deep Learning | Curated by Aleksander Molak

Jul 27, 2023
21 stories
2 saves
Geometric Deep Learning
In
Data Science at Microsoft
by
Jacob H. Marquez
Decoding the customer journey with graph node embeddingsHow to use graph networks and algorithms to derive insights from the customer journey
Jul 25, 2023
1
Jul 25, 2023
1
In
TDS Archive
by
Michael Bronstein
Direction Improves Graph LearningHow a wise use of direction when doing message passing on heterophilic graphs can result in very significant gains.
Jun 8, 2023
4
Jun 8, 2023
4
In
Lyft Engineering
by
Javen Xu
lyft2vec — Embeddings at LyftCo-authors: Hakan Baba, Adriana Deneault.
Mar 22, 2023
2
Mar 22, 2023
2
Shaw99
GraphMAE: Generative can be better than Contrastive in Graph Self-supervised LearningA new paradigm for self-supervised learning on graphs
Jul 16, 2022
Jul 16, 2022
In
TDS Archive
by
Michael Bronstein
Deep learning on graphs: successes, challenges, and next stepsWhat would it take for graph neural networks to become a game changer? Evolution and future trends in the field of deep learning on graphs.
Jun 15, 2020
6
Jun 15, 2020
6
In
Stanford CS224W: Machine Learning with Graphs
by
Anya Fries
Deep Learning on 3D MeshesA learned solution to node-level classification on irregular graphs via graph neural networks.
Jan 26, 2022
1
Jan 26, 2022
1
In
TDS Archive
by
Michael Bronstein
Neural Sheaf Diffusion for deep learning on graphsCellular sheaf theory, a branch of algebraic topology, provides new insights into how Graph Neural Networks work and how to design new…
May 16, 2022
May 16, 2022
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Using subgraphs for more expressive GNNsGNNs have limited expressive power due to their equivalence to WL test. Recent works show how to improve expressivity by using subgraphs.
Dec 20, 2021
1
Dec 20, 2021
1
In
TDS Archive
by
Michael Bronstein
Learning on graphs with missing featuresFeature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features
Feb 3, 2022
3
Feb 3, 2022
3
In
TDS Archive
by
Michael Bronstein
Predictions and hopes for Graph ML in 2021Leading researchers in Graph ML summarise the progress in 2020 and make predictions for 2021
Jan 5, 2021
2
Jan 5, 2021
2
In
TDS Archive
by
Michael Bronstein
Predictions and hopes for Geometric & Graph ML in 2022Leading researchers in Geometric & Graph ML summarise the progress in 2021 and make predictions for 2022
Jan 24, 2022
5
Jan 24, 2022
5
In
TDS Archive
by
Michael Bronstein
Simple scalable graph neural networksOne of the practical challenges of graph neural networks is scalability to large graphs. We present a simple solution for scalable GNNs.
Aug 8, 2020
2
Aug 8, 2020
2
In
TDS Archive
by
Michael Bronstein
Graph Neural Networks through the lens of Differential Geometry and Algebraic TopologyNew perspectives on old problems in Graph ML
Nov 18, 2021
Nov 18, 2021
In
TDS Archive
by
Michael Bronstein
Expressive power of graph neural networks and the Weisfeiler-Lehman testThe expressive power of graph neural networks has deep relations to classical results in graph theory, described in this post.
Jun 26, 2020
4
Jun 26, 2020
4
Michael Galkin
Knowledge Graphs @ ICLR 2021Your guide to the KG-related research in ML, May edition
May 6, 2021
May 6, 2021