Geometric Deep Learning

Geometric deep learning (GDL) focuses on developing neural network architectures that can effectively process and learn from data with inherent geometric structures, such as graphs, meshes, and point clouds. Current research emphasizes the design of equivariant models, particularly graph neural networks (GNNs), which maintain consistent representations under geometric transformations like rotations and translations, and the development of efficient pooling operators to handle large datasets. These advancements are significantly impacting various fields, improving the accuracy and efficiency of tasks ranging from molecular simulations and material science to medical image analysis and computer-aided design.

Papers

February 14, 2024

Position: Topological Deep Learning is the New Frontier for Relational Learning
Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Topological Feature Geometric Deep Learning New Frontier Product Specific Position Information Relational Learning Topological Deep Learning

February 7, 2024

E(3)-Equivariant Mesh Neural Networks
Thuan Trang, Nhat Khang Ngo, Daniel Levy, Thieu N. Vo, Siamak Ravanbakhsh, Truong Son Hy
Geometric Deep Learning Triangular Mesh

January 15, 2024

Combining Image- and Geometric-based Deep Learning for Shape Regression: A Comparison to Pixel-level Methods for Segmentation in Chest X-Ray
Ron Keuth, Mattias Heinrich
Segmentation Based Approach Chest X Ray Geometric Deep Learning Pixel Wise Point Transformer Convolutional Encoder Lightweight CNN Geometric Neural Network Shape Regression

November 21, 2023

Unsupervised Multimodal Surface Registration with Geometric Deep Learning
Mohamed A. Suliman, Logan Z. J. Williams, Abdulah Fawaz, Emma C. Robinson
Image Registration Geometric Deep Learning Cortical Surface

November 19, 2023

A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
Shuo Zhang, Yang Liu, Lei Xie
Known Molecule Geometric Deep Learning Universal Model Molecular System RNA Structure Molecular Mechanic

November 8, 2023

Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
Pim de Haan, Taco Cohen, Johann Brehmer
Geometric Deep Learning Aware Transformer Euclidean Space Geometric Algebra Conformal FRP@TPR95 Metric Projective Geometry Projective Simulation Equivariant Transformer

October 16, 2023

Riemannian Residual Neural Networks
Isay Katsman, Eric Ming Chen, Sidhanth Holalkere, Anna Asch, Aaron Lou, Ser-Nam Lim, Christopher De Sa
Geometric Deep Learning Residual Neural Network Euclidean Neural Network Riemannian Graph Neural Manifold

October 12, 2023

GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts
Deyu Zou, Shikun Liu, Siqi Miao, Victor Fung, Shiyu Chang, Pan Li
New Benchmark Distribution Shift Geometric Deep Learning Geometric Deep Learning Model

October 5, 2023

Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks
Sho Sonoda, Hideyuki Ishi, Isao Ishikawa, Masahiro Ikeda
Neural Network Geometric Deep Learning Universal Deep Group Representation Ridgelet Transform

October 3, 2023

Differentiable Modeling and Optimization of Battery Electrolyte Mixtures Using Geometric Deep Learning
Shang Zhu, Bharath Ramsundar, Emil Annevelink, Hongyi Lin, Adarsh Dave, Pin-Wen Guan, Kevin Gering, Venkatasubramanian Viswanathan
Optimization Purpose Geometric Deep Learning Differentiable Model Electrochemical Model Battery Electrolyte Ion Transport Proton Conductivity

September 11, 2023

Exploring Geometric Deep Learning For Precipitation Nowcasting
Shan Zhao, Sudipan Saha, Zhitong Xiong, Niklas Boers, Xiao Xiang Zhu
Convolutional Neural Network Temporal Graph Geometric Deep Learning Precipitation Nowcasting 1D Convolution

September 1, 2023

Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks
M. Lapenna, F. Faglioni, F. Zanchetta, R. Fioresi
Graph Neural Network Geometric Deep Learning Thermodynamic Integration Temperature Measurement Geometric Deep Learning Model Temperature Evolution

August 30, 2023

SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines
Dimitrios Mallis, Sk Aziz Ali, Elona Dupont, Kseniya Cherenkova, Ahmet Serdar Karadeniz, Mohammad Sadil Khan, Anis Kacem, Gleb Gusev, Djamila Aouada
Point Cloud Geometric Deep Learning Reverse Engineering Computer Aided Design Model 3D Scan Parameter Space Reconstruction CAD Software

July 20, 2023

Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
Marcel Beetz, Abhirup Banerjee, Vicente Grau
Point Cloud Geometric Deep Learning

July 8, 2023

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance
Yuqian Chen, Leo R. Zekelman, Chaoyi Zhang, Tengfei Xue, Yang Song, Nikos Makris, Yogesh Rathi, Alexandra J. Golby, Weidong Cai, Fan Zhang, Lauren J. O'Donnell
Geometric Deep Learning Human Connectome Project Cranial Nerve Tractography Point Wise Operation Language Assessment White Matter Tract Segmentation

July 7, 2023

VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data
Emmanuel Hartman, Emery Pierson
Neural Network Architecture Geometric Deep Learning Untranscribed Data Neural Varifold

June 23, 2023

Torsion Graph Neural Networks
Cong Shen, Xiang Liu, Jiawei Luo, Kelin Xia
Graph Neural Geometric Deep Learning Topological Information HGNN Model

June 20, 2023

A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design
Zaixi Zhang, Jiaxian Yan, Qi Liu, Enhong Chen, Marinka Zitnik
Comprehensive Survey Molecule Generation Geometric Deep Learning Structure Based Drug Design Protein Structure Prediction 3D Protein

June 8, 2023

Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification
Ashkan Shahbazi, Abihith Kothapalli, Xinran Liu, Robert Sheng, Soheil Kolouri
Geometric Deep Learning Point Cloud Classification Equivariant Map Numerous Cutting Edge Backbone Global Pooling Invariant Layer Equivariant Framework

June 6, 2023

Deep neural networks architectures from the perspective of manifold learning
German Magai
Deep Learning Deep Neural Network Visual Perspective Topological Data Analysis Manifold Learning Geometric Deep Learning Topology Problem Local Homology

Geometric Deep Learning

Papers

Position: Topological Deep Learning is the New Frontier for Relational Learning

E(3)-Equivariant Mesh Neural Networks

Combining Image- and Geometric-based Deep Learning for Shape Regression: A Comparison to Pixel-level Methods for Segmentation in Chest X-Ray

Unsupervised Multimodal Surface Registration with Geometric Deep Learning

A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems

Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers

Riemannian Residual Neural Networks

GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts

Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks

Differentiable Modeling and Optimization of Battery Electrolyte Mixtures Using Geometric Deep Learning

Exploring Geometric Deep Learning For Precipitation Nowcasting

Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks

SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines

Multi-objective point cloud autoencoders for explainable myocardial infarction prediction

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance

VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data

Torsion Graph Neural Networks

A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design

Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification

Deep neural networks architectures from the perspective of manifold learning