
Partition and Code: learning how to compress graphs
Can we use machine learning to compress graph data? The absence of order...
read it

GRAND: Graph Neural Diffusion
We present Graph Neural Diffusion (GRAND) that approaches deep learning ...
read it

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
The last decade has witnessed an experimental revolution in data science...
read it

Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
The past decade has witnessed a groundbreaking rise of machine learning ...
read it

Utilising Graph Machine Learning within Drug Discovery and Development
Graph Machine Learning (GML) is receiving growing interest within the ph...
read it

Tuning Word2vec for Large Scale Recommendation Systems
Word2vec is a powerful machine learning tool that emerged from Natural L...
read it

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
While Graph Neural Networks (GNNs) have achieved remarkable results in a...
read it

Learning interpretable disease selfrepresentations for drug repositioning
Drug repositioning is an attractive costefficient strategy for the deve...
read it

Transferability of Spectral Graph Convolutional Neural Networks
This paper focuses on spectral graph convolutional neural networks (Conv...
read it

Fake News Detection on Social Media using Geometric Deep Learning
Social media are nowadays one of the main news sources for millions of p...
read it

Isospectralization, or how to hear shape, style, and correspondence
The question whether one can recover the shape of a geometric object fro...
read it

Functional Maps Representation on Product Manifolds
We consider the tasks of representing, analyzing and manipulating maps b...
read it

Nonisometric Surface Registration via Conformal LaplaceBeltrami Basis Pursuit
Surface registration is one of the most fundamental problems in geometry...
read it

Graph Neural Networks for IceCube Signal Classification
Tasks involving the analysis of geometric (graph and manifoldstructure...
read it

DualPrimal Graph Convolutional Networks
In recent years, there has been a surge of interest in developing deep l...
read it

PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
Deep learning systems have become ubiquitous in many aspects of our live...
read it

MotifNet: a motifbased Graph Convolutional Network for directed graphs
Deep learning on graphs and in particular, graph convolutional neural ne...
read it

Dynamic Graph CNN for Learning on Point Clouds
Point clouds provide a flexible and scalable geometric representation su...
read it

Subspace Least Squares Multidimensional Scaling
Multidimensional Scaling (MDS) is one of the most popular methods for di...
read it

Localized Manifold Harmonics for Spectral Shape Analysis
The use of Laplacian eigenfunctions is ubiquitous in a wide range of com...
read it

Generative Convolutional Networks for Latent Fingerprint Reconstruction
Performance of fingerprint recognition depends heavily on the extraction...
read it

Geometric Matrix Completion with Recurrent MultiGraph Neural Networks
Matrix completion models are among the most common formulations of recom...
read it

Geometric deep learning on graphs and manifolds using mixture model CNNs
Deep learning has achieved a remarkable performance breakthrough in seve...
read it

Geometric deep learning: going beyond Euclidean data
Many scientific fields study data with an underlying structure that is a...
read it

Learning shape correspondence with anisotropic convolutional neural networks
Establishing correspondence between shapes is a fundamental problem in g...
read it

Efficient Globally Optimal 2Dto3D Deformable Shape Matching
We propose the first algorithm for nonrigid 2Dto3D shape matching, wh...
read it

Partial Functional Correspondence
In this paper, we propose a method for computing partial functional corr...
read it

Geodesic convolutional neural networks on Riemannian manifolds
Feature descriptors play a crucial role in a wide range of geometry anal...
read it

Functional correspondence by matrix completion
In this paper, we consider the problem of finding dense intrinsic corres...
read it

Shapefromintrinsic operator
ShapefromX is an important class of problems in the fields of geometry...
read it

Sparse similaritypreserving hashing
In recent years, a lot of attention has been devoted to efficient neares...
read it

Heat kernel coupling for multiple graph analysis
In this paper, we introduce heat kernel coupling (HKC) as a method of co...
read it

Structurepreserving color transformations using Laplacian commutativity
Mappings between color spaces are ubiquitous in image processing problem...
read it

Making Laplacians commute
In this paper, we construct multimodal spectral geometry by finding a pa...
read it

Multimodal diffusion geometry by joint diagonalization of Laplacians
We construct an extension of diffusion geometry to multiple modalities t...
read it

Multimodal similaritypreserving hashing
We introduce an efficient computational framework for hashing data belon...
read it

Descriptor learning for omnidirectional image matching
Feature matching in omnidirectional vision systems is a challenging prob...
read it

Multimodal diffhash
Many applications require comparing multimodal data with different struc...
read it

Kernel diffhash
This paper presents a kernel formulation of the recently introduced diff...
read it

A correspondenceless approach to matching of deformable shapes
Finding a match between partially available deformable shapes is a chall...
read it

Diffusion framework for geometric and photometric data fusion in nonrigid shape analysis
In this paper, we explore the use of the diffusion geometry framework fo...
read it

Affineinvariant geodesic geometry of deformable 3D shapes
Natural objects can be subject to various transformations yet still pres...
read it

Affineinvariant diffusion geometry for the analysis of deformable 3D shapes
We introduce an (equi)affine invariant diffusion geometry by which surf...
read it

Diffusiongeometric maximally stable component detection in deformable shapes
Maximally stable component detection is a very popular method for featur...
read it

The Video Genome
Fast evolution of Internet technologies has led to an explosive growth o...
read it
Michael M. Bronstein
verfied profile
Michael Bronstein is a professor at Imperial College London, where he holds the Chair in Machine Learning
and Pattern Recognition, and Head of Graph
Learning Research at Twitter. His main research expertise is in theoretical and computational methods for geometric data analysis, a field in which he has published extensively in the leading journals and conferences. He is credited as one of the pioneers of geometric deep learning, generalizing machine learning methods to graphstructured data. Michael received his PhD from the Technion (Israel Institute of Technology) in 2007. He has held visiting appointments at Stanford, MIT, Harvard, and Tel Aviv University, and has also been affiliated with three Institutes for Advanced Study (at TU Munich as Rudolf Diesel Fellow (2017), at Harvard as Radcliffe fellow (20172018), and at Princeton (2020)). Michael is the recipient of five ERC grants, Fellow of IEEE and IAPR, ACM Distinguished Speaker, and World Economic Forum Young Scientist. In addition to his academic career, Michael is a serial entrepreneur and founder of multiple startup companies, including Novafora, Invision (acquired by Intel in 2012), Videocites, and Fabula AI (acquired by Twitter in 2019). He has previously served as Principal Engineer at Intel Perceptual Computing.