Maya Bechler-Speicher
Meta
Tel-Aviv University
Embedded Files
I'm an AI Research Scientist at Meta, working mainly on Graph Foundation Models and LLMs+Graphs.
I recently defended my PhD titled "Towards improved Generalizability and Interpretability in Graph Neural Networks" at the School of Computer Science at Tel Aviv University, where I was fortunate be advised by Amir Globerson and Ran Gilad-Bachrach.
I am also a lecturer at the Computer Science School at Tel-Aviv University, teaching "Machine Learning with Graphs" , an advanced course I have built from scratch to spread the rumor on Graph Machine Learning.
I am broadly interested in Deep Learning, Geometric Deep Learning, and the connection between GNNs and LLMs.
In the summer of 2021, I interned at Meta on the Risk-ML team. Prior to that, I spent three years at Microsoft as an Applied & Data Scientist in the Machine Learning Incubation and Innovation group (CTO office), where I had the opportunity to invent, lead and develop novel and disruptive AI-based products.
I hold a BSc and MSc in Computer Science from Ben-Gurion University, where I conducted research with Natan Rubin and participated in the ‘Dkalim’ and ‘Intel’ excellence programs.
I also completed a second full BSc in Mathematics after my MSc and mostly in parallel to my PhD, just for fun. I really love Math.
Email: mayab4 AT mail.tau.ac DOT il
News:
Our new preprint on next generation graph benchmarking is here! Try GraphBench now!
Two spotlight papers and two workshop papers accepted to NeurIPS 2025!
I will give a talk at the Center of Computational Mathematics at the FlatIron Institute in July 2025.
I will give a Keynote Talk at GHOST Day - Applied Machine Learning conference.
Our paper Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks was accepted to ICML 2025!
I will be speaking at Joan Bruna's ML seminar CS@NYU in March 2025.
GraphBench: Next-generation graph learning benchmarking
Timo Stoll, Chendi Qian, Ben Finkelshtein, Ali Parviz, Darius Weber, Fabrizio Frasca, Hadar Shavit, Antoine Siraudin, Arman Mielke, Marie Anastacio, Erik Müller, Maya Bechler-Speicher, Michael Bronstein, Mikhail Galkin, Holger Hoos, Mathias Niepert, Bryan Perozzi, Jan Tönshoff, Christopher Morris
Preprint.
Interpretable Graph Learning Over Sets of Temporally-Sparse Data
Maya Bechler-Speicher*, Andrea Zerio*, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs
Preprint.
Maya Bechler-Speicher*, Andrea Zerio*, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs
NeurIPS Symmetry and Geometry in Neural Representations (NeurReps) Workshop 2025.
Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
Snir Hordan, Maya Bechler-Speicher, Gur Lifshitz, Nadav Dym
Advances in Neural Information Processing Systems (NeurIPS) 2025 (Spotlight)
Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers
Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson
Advances in Neural Information Processing Systems (NeurIPS) 2025 (Spotlight)
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
Maya Bechler-Speicher *, Ben Finkelshtein *, Fabrizio Frasca *, Luis Müller *, Jan Tönshoff *, Antoine Siraudin, Viktor Zaverkin, Michael M. Bronstein, Mathias Niepert, Bryan Perozzi, Mikhail Galkin, Christopher Morris
Internation Conference on Machine Learning (ICML) 2025.
Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers
Andrea Zerio, Maya Bechler-Speicher, Tine Jess, , Aleksejs Sazonovs
International Conference on Learning (ICLR) 2025, LMRL Workshop.
Towards Invariance to Node Identifiers in Graph Neural Networks
Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schönlieb, Ran Gilad-Bachrach, Amir Globerson
Preprint
A General Recipe for Contractive Graph Neural Networks - Technical Report
Maya Bechler-Speicher, Moshe Eliasof
Preprint
JJ Wilson, Maya Bechler-Speicher, Petar Velickovic
Learning On Graphs (LOG) 2024.
The Intelligible and Effective Graph Neural Additive Networks
Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Advances in Neural Information Processing Systems 37 (NeurIPS) 2024.
Graph Neural Networks Use Graphs When They Shouldn't
Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson
Internation Conference on Machine Learning (ICML) 2024.
TREE-G: Decision Trees Contesting Graph Neural Networks
Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Association for the Advancement of Artificial Intelligence (AAAI) 2024.
Oren Elisha , Ami Luttwak, Hila Yehuda, Adar Kahana, Maya Bechler-Speicher
US Patent
Oren Elisha , Ami Luttwak, Hila Yehuda, Adar Kahana, Maya Bechler-Speicher
US Patent
Oren Elisha , Ami Luttwak, Hila Yehuda, Adar Kahana, Maya Bechler-Speicher
US Patent
Maya Bechler-Speicher, Natan Rubin
Programs and Invited Talks
Keynote Talk at GHOST Day - Applied Machine Learning conference.
Speaking at Joan Bruna's ML seminar CS@NYU in March 2025.
Haggai Maron's group seminar at Technion
Chaim Baskin's group seminar at BGU.
Graph Learning on Wednesdays (GLOW) 18/11/24 on Graph Neural Networks Use Graphs When They Shouldn't.
"implicit biases in Graph Neural Networks" at Haggai Maron's group seminar at Technion and at Chaim Baskin's group seminar at BGU.
Talk at Graph Learning on Wednesdays (GLOW) on Graph Neural Networks Use Graphs When They Shouldn't, 2024.
Co-organized the Geometric Deep Leaning Tel-Aviv Meetup 2024, as part of LOG 2024 local meetups.
Talk at Cambridge Image and Analysis Seminar, Department of Applied Mathematics, University of Cambridge, on Graph Neural Networks Use Graphs When They Shouldn't,. (YouTube), 2024.
Participant at the Machine Learning Theory Summer School at Princeton University, 2024.
Talk at at the Deep Learning Theory Retreat of The AI and Data Science Center, 2023.
Talk at WIT (Women in Theory) at Simons Institute for the Theory of Computing at Berkeley University, 2022.
Women in Theory Conference at Simons Institute for the Theory of Computing at Berkeley University, 2022.
Teaching
Spring 24/25: Machine Learning with Graphs, Tel-Aviv University. (Lecturer)
Spring 23/24: Machine Learning with Graphs, Tel-Aviv University. (Lecturer)
Spring 19/20: Introduction to Data Science, Tel-Aviv University. (Teaching Assistant)
Fall 17/18 – Algorithms in Geometric Networks, Ben-Gurion University. (Teaching Assistant)
Fall 17/18 – Geometric Algorithms, Ben-Gurion University. (Teaching Assistant)
Fall 16/17 – Systems Programming, Ben-Gurion University. (Teaching Assistant)
Reviewer Service
NeurIPS 2025
ICML 2025
TML 2025
JMLR 2025
ICLR 2025
ICML 2024
NeurIPS 2023
ICML 2022
Page updated
Google Sites
Report abuse