Michael Bronstein – Medium

Michael Bronstein

11.9K followers

Pinned

In

TDS Archive

by

Michael Bronstein

·

Mar 18, 2024

The Road to Biology 2.0 Will Pass Through Black-Box Data

Future bio-AI breakthroughs will arise from novel high-throughput low-cost AI-specific “black-box” data modalities.

The Road to Biology 2.0 Will Pass Through Black-Box Data

In

TDS Archive

by

Michael Bronstein

·

Dec 6, 2023

Co-operative Graph Neural Networks

A new message-passing paradigm where every node can choose to either ‘listen’, ‘broadcast’, ‘listen & broadcast’ or ‘isolate’.

Co-operative Graph Neural Networks

In

TDS Archive

by

Michael Bronstein

·

Oct 19, 2023

Topological Generalisation with Advective Diffusion Transformers

A new diffusion-based continuous GNN model offers better generalisation capabilities

Topological Generalisation with Advective Diffusion Transformers

In

TDS Archive

by

Michael Bronstein

·

Jun 19, 2023

Dynamically rewired delayed message passing GNNs

Dynamic rewiring and delayed message passing mechanisms offer a tradeoff between standard MPNNs and graph Transformers

Dynamically rewired delayed message passing GNNs

In

TDS Archive

by

Michael Bronstein

·

Jun 8, 2023

Direction Improves Graph Learning

How a wise use of direction when doing message passing on heterophilic graphs can result in very significant gains.

Direction Improves Graph Learning

In

TDS Archive

by

Michael Bronstein

·

Apr 30, 2023

Hyperbolic Deep Reinforcement Learning

Many RL problems have hierarchical tree-like nature. Hyperbolic geometry offers a powerful prior for such problems.

Hyperbolic Deep Reinforcement Learning

In

TDS Archive

by

Michael Bronstein

·

Apr 20, 2023

Learning Network Games

How to learn the network underlying the interactions of players in social applications, economics, and beyond.

Learning Network Games

In

TDS Archive

by

Michael Bronstein

·

Oct 14, 2022

Graph Neural Networks as gradient flows

GNNs derived as gradient flows minimising a learnable energy that describes attractive and repulsive forces between graph nodes.

Graph Neural Networks as gradient flows

In

TDS Archive

by

Michael Bronstein

·

Jul 25, 2022

Towards Geometric Deep Learning IV: Chemical Precursors of GNNs

In the last post in the “Towards Geometric Deep Learning” series, we look at early prototypes of GNNs in the field of chemistry.

Towards Geometric Deep Learning IV: Chemical Precursors of GNNs

In

TDS Archive

by

Michael Bronstein

·

Jul 18, 2022

Towards Geometric Deep Learning III: First Geometric Architectures

In the third post of our series “Towards Geometric Deep Learning” we look at the first “geometric” architectures: Neocognitron and CNNs

Towards Geometric Deep Learning III: First Geometric Architectures

Michael Bronstein

Michael Bronstein

11.9K followers

DeepMind Professor of AI @Oxford. Serial startupper. ML for graphs, biochemistry, drug design, and animal communication.

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech