Maya Bechler-Speicher

Researcher, Facebook

Joined

May 2022

Names

Maya Bechler-Speicher (Preferred)

Emails

****@mail.tau.ac.il (Confirmed)

****@meta.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

Facebook (meta.com)

2024 – Present

PhD student

Tel Aviv University (tau.ac.il)

2020 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Amir Globerson

2020 – 2025

PhD Advisor

Ran Gilbad-Bachrach

2020 – 2025

Expertise

Graph Neural Networks

2020 – 2025

Graph Machine Learning

2020 – 2025

Publications

Improving LLM Predictions via Inter-Layer Structural Encoders
Tom Ulanovski, Eyal Blyachman, Maya Bechler-Speicher
- ICLR 2026 Workshop GRaM Poster
- Readers: Everyone
A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
Guy Bar-Shalom, Ami Tavory, Itay Evron, Maya Bechler-Speicher, Ido Guy, Haggai Maron
- ICLR 2026 Poster
- Readers: Everyone
SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Andrea Zerio, Maya Bechler-Speicher, Maor Huri, Marie Vibeke Vestergaard, Tine Jess, Ran Gilad-Bachrach, Samir Bhatt, Aleksejs Sazonovs
- ICLR 2026 Poster
- Readers: Everyone
GraphBench: Next-generation graph learning benchmarking
Antoine Siraudin, Chendi Qian, Ben Finkelshtein, Ali Parviz, Darius Weber, Fabrizio Frasca, Hadar Shavit, Timo Stoll, Arman Mielke, Marie Anastacio, Erik Müller, Maya Bechler-Speicher, Michael M. Bronstein, Mikhail Galkin, Holger H. Hoos, Mathias Niepert, Bryan Perozzi, Jan Tönshoff, Christopher Morris
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Interpretable Graph Learning on Irregular Clinical Time Series
Andrea Zerio, Maya Bechler-Speicher, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs
- TS4H NeurIPS 2025 Poster
- Readers: Everyone
Graph Mixing Additive Networks
Maya Bechler-Speicher, Andrea Zerio, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs
- NeurReps 2025 Poster
- Readers: Everyone
Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
Snir Hordan, Maya Bechler-Speicher, Gur Lifshitz, Nadav Dym
- NeurIPS 2025 spotlight
- Readers: Everyone
Depth-Width Tradeoffs for Transformers on Graph Tasks
Gilad Yehudai, Clayton Sanford, Maya Bechler-Speicher, Orr Fischer, Ran Gilad-Bachrach, Amir Globerson
- NeurIPS 2025 spotlight
- Readers: Everyone
Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers
Andrea Zerio, Maya Bechler-Speicher, Tine Jess, Aleksejs Sazonovs
- ICLR 2025 Workshop LMRL
- Readers: Everyone
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
- ICML 2025 Position Paper Track poster
- Readers: Everyone

View all 13 publications

Co-Authors

View all 44 co-authors