Maya Bechler-Speicher
Tel-Aviv University & Meta
Embedded Files
I'm an AI Research Scientist at Meta and PhD candidate at the School of Computer Science at Tel Aviv University, and I am fortunate be advised by Amir Globerson and Ran Gilad-Bachrach.
I am broadly interested in Deep Learning, Graph Machine Learning and Geometric Deep Learning. I am particularly interested in the theory and applications of Graph Neural Networks.
I am also a lecturer at the Computer Science School at Tel-Aviv University, teaching Machine Learning with Graphs .
I was lucky to spend the summer of 2021 at Meta (Facebook) at the Risk-ML team, where I developed Graph Neural Networks for fraud detection. Previously, I spent 3 years at Microsoft as a Data Scientist in the Machine Learning Incubation and Innovation group, where I was lucky to be part of the development of new innovative ML-based products.
Previously, I received an MSc in Computer Science from Ben-Gurion University, where I was fortunate to do research with Natan Rubin.
Email: mayab4 AT mail.tau.ac DOT il
News
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!
Our paper 'Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers' was accepted to ICLR 2025 Learning Meaningful Representations of Life workshop.
I will be speaking at Joan Bruna's ML seminar CS@NYU in March 2025.
In Jan 2025, I will speak on implicit biases in Graph Neural Networks at Haggai Maron's group seminar at Technion and at Chaim Baskin's group seminar at BGU.
I am co-organizing the Geometric Deep Leaning Tel-Aviv Meetup 2024, as part of LOG 2024 local meetups.
I will speak at Graph Learning on Wednesdays (GLOW) 18/11/24 on Graph Neural Networks Use Graphs When They Shouldn't.
Our paper Cayley Graph Propagation was accepted to Learning On Graphs (LOG) 2024!
My recent talk at the University of Cambridge on "Graph Neural Networks Use Graphs When They Shouldn't" is now available on YouTube!
I will be visiting the University of Cambridge at Carola-Bibiane Schonlies's Lab in October 2024.
I was accepted to Princetone's ML-Theory Summer School.
My Paper The Intelligible and Effective Graph Neural Additive Networks was accepted to NeurIPS 2024.
My poster was accepted to "Mathematics of Imaging Data and ML".
My paper Graph Neural Networks Use Graphs When They Shouldn't was accepted to ICML2024.
My paper " TREE-G: Decision Trees Contesting Graph Neural Networks" was accepted to AAAI2024.
I gave a talk about Implicit Biases in Graph Neural Networks at the Deep Learning Theory Retreat of The AI and Data Science Center (Tel-Aviv University).
I won the IDSI cloud computing fund for research in the application and core of Data Science.
I completed a B.Sc. in Mathematics from Tel-Aviv University, which I pursued as enrichment in parallel to my MSc and PhD in Computer Science.
I gave a talk about Implicit Biases in Graph Neural Networks at WIT (Women in Theory) at Simons Institute for the Theory of Computing at Berkeley University.
Papers
Maya Bechler-Speicher*, Andrea Zerio*, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs
Preprint.
Snir Hordan, Maya Bechler-Speicher, Gur Lifshitz, Nadav Dym
Preprint.
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.
Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson
Preprint, Under Review
Andrea Zerio, Maya Bechler-Speicher, Tine Jess, , Aleksejs Sazonovs
International Conference on Learning (ICLR) 2025, LMRL Workshop.
Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schönlieb, Ran Gilad-Bachrach, Amir Globerson
Preprint, Under Review
Maya Bechler-Speicher, Moshe Eliasof
Preprint
JJ Wilson, Maya Bechler-Speicher, Petar Velickovic
Learning On Graphs (LOG) 2024.
Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Advances in Neural Information Processing Systems 37 (NeurIPS) 2024.
Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson
Internation Conference on Machine Learning (ICML) 2024.
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
Cambridge Image and Analysis Seminar, Department of Applied Mathematics, University of Cambridge, on Graph Neural Networks Use Graphs When They Shouldn't,. (YouTube), 2024.
Machine Learning Theory Summer School at Princeton University, 2024.
Implicit Biases in Graph Neural Networks at the Deep Learning Theory Retreat of The AI and Data Science Center (Tel-Aviv University), 2023.
Implicit Biases in Graph Neural Networks 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