Fabrizio Frasca

Technion – Israel Institute of Technology — Israel

Computer Science · Physical Sciences

11h-index911citations35works0.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Graph Neural Networks(16), Complex Network Analysis Techniques(6), Graph Theory and Algorithms(6), Genomics and Chromatin Dynamics(4), Machine Learning in Materials Science(4)

Publications35 total

Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
arXiv (Cornell University)·2025Open Access
On The Expressive Power of GNN Derivatives
arXiv (Cornell University)·2025Open Access
Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
arXiv (Cornell University)·2025Open Access
Neural Message-Passing on Attention Graphs for Hallucination Detection
arXiv (Cornell University)·2025Open Access
FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
arXiv (Cornell University)·2025Open Access
Understanding and Improving Laplacian Positional Encodings for Temporal GNNs
Lecture notes in computer science·2025
Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
arXiv (Cornell University)·2025Open Access
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
arXiv (Cornell University)·2025Open Access
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
arXiv (Cornell University)·2025· 1 citedOpen Access
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
arXiv (Cornell University)·2025Open Access
Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs
arXiv (Cornell University)·2024Open Access
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
arXiv (Cornell University)·2024Open Access
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
arXiv (Cornell University)·2024Open Access
Future Directions in the Theory of Graph Machine Learning
arXiv (Cornell University)·2024Open Access
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
2024
Edge Directionality Improves Learning on Heterophilic Graphs
arXiv (Cornell University)·2023· 22 citedOpen Access
Graph Positional Encoding via Random Feature Propagation
arXiv (Cornell University)·2023Open Access
Graph Neural Networks for Link Prediction with Subgraph Sketching
arXiv (Cornell University)·2022· 17 citedOpen Access
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
arXiv (Cornell University)·2022· 21 citedOpen Access
Accurate and highly interpretable prediction of gene expression from histone modifications
BMC Bioinformatics·2022· 14 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Michael M. Bronstein(16), Haggai Maron(16), Guy Bar-Shalom(9), Yam Eitan(6), Moshe Eliasof(5), Matteo Matteucci(4), Marco J. Morelli(4), Marco Masseroli(4), Federico Monti(3), Davide Eynard(3), Beatrice Bevilacqua(3), Yftah Ziser(3), Yaniv Galron(3), Eran Treister(3), Giorgos Bouritsas(2), Stefanos Zafeiriou(2), Emanuele Rossi(2), Ben Chamberlain(2), Cristian Bodnar(2), Yu Guang Wang(2)