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 Dr. Ismail Ilkan Ceylan. With professional experience in machine learning and large language model research at Microsoft. Always eager to explore innovative solutions at the intersection of theory and application.

CV:

news

Jun 13, 2025	Started internship at Microsoft HQ (Redmond, USA) on solving graph ML problems with Agents
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
Sep 26, 2024	Almost Surely Asymptotically Constant Graph Neural Networks is accepted to NeurIPS 2024
Sep 26, 2024	Learning on Large Graphs using Intersecting Communities is accepted to NeurIPS 2024

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.
Covered Forest: Fine-grained generalization analysis of graph neural networks

Antonis Vasileiou, Ben Finkelshtein, Floris Geerts, and 2 more authors

ICML, 2025

Abs HTML

We extend graph similarity theory to assess the influence of graph structure, aggregation, and loss functions on MPNNs’ generalization abilities.
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.