01
A Non-Aggregative Quantification Method for Graph Nodes
Accepted at ECML/PKDD Workshop on Quantification and Classification under Dataset Shift (QCDS 2026)
Research profile / Computer science
Marco Podda
I study how machines learn from graphs—and how those models can be explained, generated, and applied to the life sciences.
Academic profile
- Position
- Postdoctoral Research Fellow Starting August 2026
- Affiliation
- University of Pisa, Department of Computer Science
Publications / Latest
Recent publications
02
Network Quantification on Neuromorphic Hardware: Proof-of-concept with Randomized Ising Models
Accepted at ECML/PKDD Workshop on Deep Learning Meets Neuromorphic Hardware (DLMNH 2026)
03
A method for the systematic generation of graph XAI benchmarks via Weisfeiler–Leman coloring
Data Mining and Knowledge Discovery
DOI ↗