Maya Bechler-Speicher
Scholar

Maya Bechler-Speicher

Google Scholar ID: 5Fj_AUoAAAAJ
Research Scientist, Meta | PhD CS@Tel-Aviv University
Machine LearningGraph Machine LearningGraph Neural Networks
Citations & Impact
All-time
Citations
197
 
H-index
6
 
i10-index
6
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • Multiple papers accepted to top-tier conferences: two NeurIPS 2025 Spotlight papers, one ICML 2025 paper, one ICLR 2025 workshop paper, etc.
  • NeurIPS 2025 Spotlight papers: "Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum" and "Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers".
  • ICML 2025 paper: "Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks".
  • ICLR 2025 LMRL Workshop paper: "Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers".
  • Several preprints including "Towards Invariance to Node Identifiers in Graph Neural Networks" and "A General Recipe for Contractive Graph Neural Networks".
  • Invited speaker at multiple venues, including a keynote at GHOST Day and a talk at NYU CS@NYU’s ML seminar hosted by Joan Bruna.