Daniele Castellana

Research Fellow (RTD-A) in Machine Learning

Department of Statistics, Informatics and Application, University of Florence
profile_pic.jpg

Research interests: My research focuses on Machine Learning, with emphasis on structured data, tensor teory, and Bayesian approaches. Have a look to my PhD thesis!

Research group: Currently, I am memeber of Florence Data Science. At the University of Pisa, I was a member of CIML group and Pervasive AI lab.

Other: I like participating in competitive programming contests and playing soccer.

News

Jan 1, 2023 Are you interested in Machine Learning? Check out the opportunities page!

Selected publications

See all
  1. Lying Graph Convolution: Learning to Lie for Node Classification Tasks
    Daniele Castellana
    In 2024 International Joint Conference on Neural Networks (IJCNN), 2024
    Accepted
  2. CD-IMM: The Benefits of Domain-based Mixture Models in Bayesian Continual Learning
    Daniele Castellana, Antonio Carta, and Davide Bacciu
    In First ContinualAI Unconference-Preregistration Track, 2024
  3. Investigating the Interplay between Features and Structures in Graph Learning
    Daniele Castellana, and Federico Errica
    In 20th International Workshop on Mining and Learning with Graphs, 2023
  4. The Infinite Contextual Graph Markov Model
    Daniele CastellanaFederico ErricaDavide Bacciu, and 1 more author
    In Proceedings of the 39th International Conference on Machine Learning, 17–23 jul 2022
  5. A tensor framework for learning in structured domains
    Daniele Castellana, and Davide Bacciu
    Neurocomputing, 17–23 jul 2021
  6. Learning from Non-Binary Constituency Trees via Tensor Decomposition
    Daniele Castellana, and Davide Bacciu
    In Proceedings of the 28th International Conference on Computational Linguistics, Dec 2020