Biagio (Mattia) La Rosa bio photo

Biagio (Mattia) La Rosa

I am a researcher interested in methodologies to improve the interpretability of Deep Learning techniques. Passionate also about neuroscience, psychology, games, and astronomy.

Twitter   G. Scholar LinkedIn Github e-Mail

My Publications

Incoming / Pre-Prints

2024

  • Explaining Deep Neural Networks by Leveraging Intrinsic Methods
    Biagio La Rosa
    PhD Thesis
    [BibTeX] [ArXiv] [PDF]

@phdthesis{LaRosa2024thesis,
  title        = {Explaining Deep Neural Networks by Leveraging Intrinsic Methods},
  author       = {Biagio {La Rosa}},
  year         = 2024,
  month        = {May},
  address      = {Rome, IT},
  school       = {Sapienza University of Rome},
  type         = {PhD thesis}
}

2023

  • Towards a fuller understanding of neurons with Clustered Compositional Explanations
    Biagio La Rosa, Leilani Gilpin, and Roberto Capobianco
    NeurIPS 2023
    [BibTeX] [PDF NeurIPS] [ArXiv] [Code]

@inproceedings{
LaRosa2023Towards,
title={Towards a fuller understanding of neurons with Clustered Compositional Explanations},
author={Biagio {La Rosa} and Leilani H. Gilpin and Roberto Capobianco},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=51PLYhMFWz}
}
  • Explainable AI in Drug Discovery: Self-interpretable Graph Neural Network for molecular property prediction using Concept Whitening
    Michela Proietti, Alessio Ragno, Biagio La Rosa, Rino Ragno, and Roberto Capobianco
    Machine Learning (Journal)
    [BibTeX] [PDF Journal] [Code]

@Article{Proietti2023,
  author    = {Michela Proietti and Alessio Ragno and Biagio {La Rosa} and Rino Ragno and Roberto Capobianco},
  journal   = {Machine Learning},
  title     = {Explainable {AI} in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening},
  year      = {2023},
  month     = {oct},
  doi       = {10.1007/s10994-023-06369-y},
  publisher = {Springer Science and Business Media {LLC}},
}
  • The State of The Art of Visual Analytics for eXplainable Deep Learning
    Biagio La Rosa, Graziano Blasilli, Romain Bourqui, David Auber, Giuseppe Santucci, Roberto Capobianco, Enrico Bertini, Romain Giot, and Marco Angelini
    Computer Graphic Forum (Journal)
    Presented also at 25th EG Conference on Visualization (EuroVIS 2023)
    [BibTeX] [PDF Journal] [Interactive]

 
@Article{LaRosa2023,
  author    = {{La Rosa}, B. and Blasilli, G. and Bourqui, R. and Auber, D. and Santucci, G. and Capobianco, R. and Bertini, E. and Giot, R. and Angelini, M.},
  journal   = {Computer Graphics Forum},
  title     = {State of the Art of Visual Analytics for eXplainable Deep Learning},
  year      = {2023},
  issn      = {1467-8659},
  month     = feb,
  number    = {1},
  pages     = {319--355},
  volume    = {42},
  doi       = {10.1111/cgf.14733},
  publisher = {Wiley},
}

2022

  • Prototype-based Interpretable Graph Neural Networks
    Alessio Ragno, Biagio La Rosa, and Roberto Capobianco
    IEEE Transactions on Artificial Intelligence (Journal)
    [BibTeX] [PDF Journal] [Code]

@Article{Ragno2022,
  author={Ragno, Alessio and {La Rosa}, Biagio and Capobianco, Roberto},
  journal={IEEE Transactions on Artificial Intelligence}, 
  title={Prototype-based Interpretable Graph Neural Networks}, 
  year={2022},
  volume={},
  number={},
  pages={1-11},
  doi={10.1109/TAI.2022.3222618}
}
  • A self-interpretable module for deep image classification on small data.
    Biagio La Rosa, Roberto Capobianco and Daniele Nardi.
    Applied Intelligence (Journal)
    [BibTeX] [PDF Journal] [ArXiv] [Code] 

@Article{LaRosa2022,
  author    = {Biagio {La Rosa} and Roberto Capobianco and Daniele Nardi},
  journal   = {Applied Intelligence},
  title     = {A self-interpretable module for deep image classification on small data},
  year      = {2022},
  month     = {aug},
  doi       = {10.1007/s10489-022-03886-6},
  publisher = {Springer Science and Business Media {LLC}},
}

2021

  • Detection Accuracy for Evaluating Compositional Explanations of Units
    Sayo M. Makinwa, Biagio La Rosa, Roberto Capobianco.
    AIxIA 2021
    [BibTeX] [PDF] [ArXiv] [Code]

@InCollection{Makinwa2022,
  author    = {Sayo M. Makinwa and Biagio {La Rosa} and Roberto Capobianco},
  booktitle = {AIxIA 2021 - Advances in Artificial Intelligence},
  publisher = {Springer International Publishing},
  title     = {Detection Accuracy for~Evaluating Compositional Explanations of~Units},
  year      = {2022},
  pages     = {550--563},
  doi       = {10.1007/978-3-031-08421-8_38},
}
  • A Discussion about Explainable Inference on Sequential Data via Memory-Tracking.
    Biagio La Rosa, Roberto Capobianco and Daniele Nardi.
    AIxIA 2021 Discussion Papers
    [BibTeX] [PDF] [Code] [Blog Post].

@inproceedings{LaRosa2021,
  title     = {A Discussion about Explainable Inference on Sequential Data via Memory-Tracking},
  author    = {{La Rosa}, Biagio and Capobianco, Roberto and Nardi, Daniele},
  booktitle = {AIxIA 2021 Discussion Papers},
  publisher = {CEUR Workshop Proceedings},             
  volume     = {3078},
  pages     = {33-44},
  year      = {2021},
  url       = {http://ceur-ws.org/Vol-3078/paper-24.pdf},
}

2020

  • “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)
    [BibTeX] [PDF] [Code] [Blog Post].

@inproceedings{LaRosa20,
  title     = {Explainable Inference on Sequential Data via Memory-Tracking},
  author    = {{La Rosa}, Biagio and Capobianco, Roberto and Nardi, Daniele},
  booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on
               Artificial Intelligence, {IJCAI-20}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},             
  pages     = {2006--2013},
  year      = {2020},
  month     = {7},
  doi       = {10.24963/ijcai.2020/278},
  url       = {https://doi.org/10.24963/ijcai.2020/278},
}

Theses

Master

Short Abstract: The thesis presents a novel mechanism to get hints of explanation exploiting the capability of memory-based networks – Differential Neural Computers – to store data in memory and reusing it for inference. By tracking both the memory access at prediction time, and the information stored by the network at each step of the input sequence, it is possible to retrieve the most relevant input steps associated to each prediction. The mechanism is tested on two problems: a modified version of T-Maze and the Story Cloze Test task. The work studies also the influence of parameters and the adequacy of the extracted explanations.
Area: Explainable Artificial Intelligence
Supervisor: Roberto Capobianco

Bachelor

Short Abstract: The work presents a supersense tagger based on Wikipedia and BabelNet. SuperSense tagging is a Natural Language Processing task that consists in annotating each entity in a text according to a general semantic taxonomy. In our case BabelNet is used as taxonomy, extracting the most used words and collecting the nouns that can indicate a category. Exploiting the is-a relations of BabelNet, then Wikipedia is annotated with the extracted concepts and used as dataset for the training of an SVM classifier based on the framework It Makes Sense.
Area: Natural Language Processing
Supervisor: Roberto Navigli