1. Enheten
  2. Ansatte
  3. Antonio Longa
Bilde av Longa, Antonio
Bilde av Longa, Antonio
Institutt for matematikk og statistikk antonio.longa@uit.no Tromsø Her finner du meg

Antonio Longa

Stillingsbeskrivelse

I am a postdoctoral researcher working at the intersection of machine learning and network science. My research focuses on relational deep learning, with an emphasis on graph neural networks, temporal networks, and explainability. I aim to bridge theoretical foundations with real-world applications in complex systems, including energy and materials science.

  • Lorenzo Epifani, Antonio Longa, Alessandro Falcetta, Filippo Maria Bianchi, Manuel Roveri :
    When Low Error Misses Events: Training and Evaluating Sparse Time-Series Forecasters
    Communications in Computer and Information Science (CCIS) 2026 ARKIV
  • Antonio Longa, Marco Rossi, Francesca Soldan, Ramon Zambetti, Andrea Cazzaniga, Andrea Passerini :
    Fast and accurate node-level hosting capacity estimation in distribution networks using graph neural networks
    Electric power systems research 28. juni 2026 DOI / ARKIV
  • Taraneh Younesian, Steve Azzolin, Antonio Longa, Francesco Ferrini, Vincenzo Marco De Luca, Stefano Teso :
    Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance
    Mining and Learning with Graphs (MLG) 2026 DOI / ARKIV

    • De 50 siste resultatene vises på siden. Se alle arbeider i NVA her →

    Forskningsinteresser

    Graph neural networks, temporal networks, relational deep learning, explainable AI, and complex systems, with applications to real-world domains such as energy and materials science.


    ORCID: https://orcid.org/0000-0003-0337-1838

    CV

    Antonio Longa is a postdoctoral researcher in machine learning and network science. He obtained his Ph.D. in Information and Communication Technology from the University of Trento (2023). His research focuses on graph neural networks, temporal networks, and explainable AI. His work has been published in top venues such as NeurIPS, ICML, and ICLR

    Forskningsparken 1 B495


    Klikk for større kart