Ben Finkelshtein

Passionate researcher and PhD candidate at the University of Oxford, specializing in Geometric Deep Learning. Supervised by DeepMind Chair of AI Prof. Michael M. Bronstein and Prof. Ismail Ilkan Ceylan. With professional experience in research at Microsoft and Google. Always eager to explore innovative solutions at the intersection of theory and application.

CV:

news

Sep 18, 2025	Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models is accepted to NeurIPS 2025
Sep 15, 2025	Started an internship at Google Research – creating the next large Graph Foundation Model!
Jun 13, 2025	Started an internship at Microsoft Research US HQ on the capabilities of LLMs in processing graph information
May 01, 2025	Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks is accepted to ICML 2025
May 01, 2025	Covered Forest: Fine-grained generalization analysis of graph neural networks is accepted as spotlight (top 2%) at ICML 2025

latest posts

Jan 16, 2024	Graph & Geometric ML in 2024: Where We Are and What's Next (Part I - Theory & Architectures) \| Towards Data Science
Dec 06, 2023	Page not found \| Towards Data Science

selected publications

Cooperative Graph Neural Networks

Ben Finkelshtein, Xingyue Huang, Michael Bronstein, and 1 more author

ICML, 2023

Abs HTML

A more dynamic and flexible message-passing paradigm in which each node can choose a different communication strategy.
Learning on Large Graphs using Intersecting Communities

Ben Finkelshtein, İsmail İlkan Ceylan, Michael Bronstein, and 1 more author

NeurIPS, 2024

Abs HTML

A new and fundamentally different pipeline for learning on very large non-sparse graphs using intersecting communities.
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, and 9 more authors

ICML, 2025

Abs HTML

This paper calls towards more meaningful benchmarks, rigorous evaluation protocols, and stronger collaboration with domain experts to drive advances in graph learning research.
Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models

Ben Finkelshtein, İsmail İlkan Ceylan, Michael Bronstein, and 1 more author

NeurIPS, 2025

Abs HTML

We derive the first graph foundation model that is provably universal and achieves SOTA zero-shot performance.