Publications

2024

  1. Pre-Print
    Explaining Deep Neural Networks by Leveraging Intrinsic Methods
    Biagio La Rosa
    2024

2023

  1. Conference
    Towards a fuller understanding of neurons with Clustered Compositional Explanations
    Biagio La Rosa, Leilani H. Gilpin, and Roberto Capobianco
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
  2. Journal
    Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening
    Michela Proietti, Alessio Ragno, Biagio La Rosa, and 2 more authors
    Machine Learning, 2023
  3. Conference & Journal
    State of the Art of Visual Analytics for eXplainable Deep Learning
    B. La Rosa, G. Blasilli, R. Bourqui, and 6 more authors
    Computer Graphics Forum
    Presented also at the EuroVis Conference , 2023

2022

  1. Journal
    Prototype-based Interpretable Graph Neural Networks
    Alessio Ragno, Biagio La Rosa, and Roberto Capobianco
    IEEE Transactions on Artificial Intelligence, 2022
  2. Journal
    A self-interpretable module for deep image classification on small data
    Biagio La Rosa, Roberto Capobianco, and Daniele Nardi
    Applied Intelligence, 2022
  3. Conference
    Detection Accuracy for Evaluating Compositional Explanations of Units
    Sayo M. Makinwa, Biagio La Rosa, and Roberto Capobianco
    In AIxIA 2021 - Advances in Artificial Intelligence, 2022

2021

  1. Conference
    A Discussion about Explainable Inference on Sequential Data via Memory-Tracking
    Biagio La Rosa, Roberto Capobianco, and Daniele Nardi
    In AIxIA 2021 Discussion Papers, 2021

2020

  1. Conference
    Explainable Inference on Sequential Data via Memory-Tracking
    Biagio La Rosa, Roberto Capobianco, and Daniele Nardi
    In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, 2020