Paolo Pellizzoni

About Me

I am a postdoctoral researcher at Harvard University, working with Prof. Melanie Weber on geometric deep learning. Previously, I completed my ELLIS Ph.D. in computer science at the Max Planck Institute of Biochemistry (and at ETH Zürich as Scientific Assistant), supervised by Prof. Karsten Borgwardt.

Research Interests

• Machine Learning: graph learning, geometric deep learning, statistical learning theory
• Theoretical Computer Science: approximation algorithms, dynamic algorithms
• Data Mining and Bioinformatics: pattern mining (e.g., itemsets, subgraphs), genetic marker discovery

Publications

• Paolo Pellizzoni^*, T. Schulz^*, and K. Borgwardt. Gelato: Graph Edit Distance via Autoregressive Neural Combinatorial Optimization, in ICLR 2026.
  [PDF]

• A. Stan-Bernhardt^*, Paolo Pellizzoni^*, K. Borgwardt, and C. Ochsenfeld. Automated Discovery of Reactive Events via Hypergraph Mining of Ab Initio Atomistic Simulations, in J. Chem. Theory Comput. 2026.
  [PDF]

• F. Graf^*, Paolo Pellizzoni^*, M. Uray, S. Huber, and R. Kwitt. The Flood Complex: Large-Scale Persistent Homology on Millions of Points, in NeurIPS 2025.
  [PDF]

• S. Moretti^*, Paolo Pellizzoni^*, and F. Silvestri. Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights, in ICML 2025.
  [PDF]

• Paolo Pellizzoni, T. Schulz, and K. Borgwardt. Graph Neural Networks Can (Often) Count Substructures, in ICLR, 2025. (Spotlight)
  [PDF]

• Paolo Pellizzoni, A. Pietracaprina, and G. Pucci. “Fully Dynamic Clustering and Diversity Maximization in Doubling Metrics”, in ACM TKDD, 2025.
  [PDF]

• Paolo Pellizzoni, T. Schulz, D. Chen and K. Borgwardt. On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks, in NeurIPS, 2024.
  [PDF]

• Paolo Pellizzoni, C. Oliver and K. Borgwardt. “Structure- and function-aware substitution matrices via learnable graph matching”, in RECOMB, 2024.
  [PDF]

• Paolo Pellizzoni and K. Borgwardt. “FASM and Fast-YB: Significant Pattern Mining with False Discovery Rate Control”, in IEEE ICDM, 2023.
  [PDF]

• D. Chen^*, Paolo Pellizzoni^*, and K. Borgwardt. “Fisher Information Embedding for Node and Graph Learning”, in ICML, 2023.
  [PDF]

• Paolo Pellizzoni, G. Muzio, and K. Borgwardt. “Higher-order genetic interaction discovery with network-based biological priors”, in ISMB, 2023.
  [PDF]

• Paolo Pellizzoni and F. Vandin. “VC-dimension and Rademacher Averages of Subgraphs, with Applications to Graph Mining”, in IEEE ICDE, 2023.
  [PDF]

• Paolo Pellizzoni, A. Pietracaprina and G. Pucci. “Adaptive k-center and diameter estimation in sliding windows”, International Journal of Data Science and Analytics, 2022.
  [PDF]

• Paolo Pellizzoni, A. Pietracaprina, and G. Pucci. “k-Center Clustering with Outliers in Sliding Windows”, Algorithms, 2022.
  [PDF]

• Paolo Pellizzoni, A. Pietracaprina, and G. Pucci. “Dimensionality-adaptive k-center in sliding windows”, in IEEE DSAA, 2020.
  [PDF]

Powered by Jekyll and Minimal Light theme.