Ben Finkelshtein

University of Oxford. Computer Science Department.

prof_pic.jpg

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. My professional experience spans roles in AI research, anomaly detection, and NLP applications, driving measurable impact. Always eager to explore innovative solutions at the intersection of theory and application.

news

May 01, 2025 Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks is accepted to ICML 2025! :sparkles: :smile:
May 01, 2025 Covered Forest: Fine-grained generalization analysis of graph neural networks is accepted as spotlight (top 2%) at ICML 2025! :sparkles: :smile:
Sep 26, 2024 Almost Surely Asymptotically Constant Graph Neural Networks is accepted to NeurIPS 2024! :sparkles: :smile:
Sep 26, 2024 Learning on Large Graphs using Intersecting Communities is accepted to NeurIPS 2024! :sparkles: :smile:

latest posts

selected publications

  1. cognn.jpeg
    Cooperative Graph Neural Networks
    Ben Finkelshtein, Xingyue Huang, Michael Bronstein, and 1 more author
    ICML, 2023
  2. icgnn.png
    Learning on Large Graphs using Intersecting Communities
    Ben Finkelshtein, İsmail İlkan Ceylan, Michael Bronstein, and 1 more author
    NeurIPS, 2024
  3. covered.png
    Covered Forest: Fine-grained generalization analysis of graph neural networks
    Antonis Vasileiou, Ben Finkelshtein, Floris Geerts, and 2 more authors
    ICML, 2025
  4. position.png
    Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
    Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, and 9 more authors
    ICML, 2025