Bruno Casella


Ph.D. student in Modeling and Data Science, University of Turin
Parallel Computing group
Via Pessinetto 12, 10149 Torino – Italy 
Email: bruno.casella@unito.it

Short Bio

Bruno Casella is a PhD student in Modeling and Data Science at UniTO, financed by Leonardo Company.
He graduated in Computer Engineering in 2020 with a thesis on the performances of AlphaZero in different scenarios.
He also received the Master’s Degree in Data Science for management in 2021 with a thesis on Federated Transfer Learning.

Fields of interest

  • Federated Learning
  • Deep learning
  • High Performance Computing

Publications

2022

  • B. Casella, R. Esposito, C. Cavazzoni, and M. Aldinucci, “Benchmarking fedavg and fedcurv for image classification tasks,” in Proceedings of the 1st italian conference on big data and data science, ITADATA 2022, september 20-21, 2022, 2022.
    [BibTeX] [Download PDF]
    @inproceedings{casella2022benchmarking,
    author = {Bruno Casella and
    Roberto Esposito and
    Carlo Cavazzoni and
    Marco Aldinucci},
    editor = {Marco Anisetti and
    Angela Bonifati and
    Nicola Bena and
    Claudio Ardagna and
    Donato Malerba},
    title = {Benchmarking FedAvg and FedCurv for Image Classification Tasks},
    booktitle = {Proceedings of the 1st Italian Conference on Big Data and Data Science, {ITADATA} 2022,
    September 20-21, 2022},
    series = {{CEUR} Workshop Proceedings},
    publisher = {CEUR-WS.org},
    year = {2022},
    url = {https://iris.unito.it/bitstream/2318/1870961/1/Benchmarking_FedAvg_and_FedCurv_for_Image_Classification_Tasks.pdf},
    keywords = {eupilot, federated learning}
    }

  • B. Casella, A. Chisari, S. Battiato, and M. Giuffrida., “Transfer learning via test-time neural networks aggregation,” in Proceedings of the 17th international joint conference on computer vision, imaging and computer graphics theory and applications, VISIGRAPP 2022, volume 5: visapp, online streaming, february 6-8, 2022, 2022, pp. 642-649. doi:10.5220/0010907900003124
    [BibTeX] [Abstract] [Download PDF]

    It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution due to the domain shift. In order to tackle this known issue, several transfer learning approaches have been proposed, where the knowledge of a trained model is transferred into another to improve performance with different data. However, most of these approaches require additional training steps, or they suffer from catastrophic forgetting that occurs when a trained model has overwritten previously learnt knowledge. We address both problems with a novel transfer learning approach that uses network aggregation. We train dataset-specific networks together with an aggregation network in a unified framework. The loss function includes two main components: a task-specific loss (such as cross-entropy) and an aggregation loss. The proposed aggregation loss allows our model to learn how trained deep network parameters can be aggregated with an aggregation operator. We demonstrate that the proposed approach learns model aggregation at test time without any further training step, reducing the burden of transfer learning to a simple arithmetical operation. The proposed approach achieves comparable performance w.r.t. the baseline. Besides, if the aggregation operator has an inverse, we will show that our model also inherently allows for selective forgetting, i.e., the aggregated model can forget one of the datasets it was trained on, retaining information on the others.

    @inproceedings{22:VISAPP:transferlearning,
    abstract = {It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution due to the domain shift. In order to tackle this known issue, several transfer learning approaches have been proposed, where the knowledge of a trained model is transferred into another to improve performance with different data. However, most of these approaches require additional training steps, or they suffer from catastrophic forgetting that occurs when a trained model has overwritten previously learnt knowledge. We address both problems with a novel transfer learning approach that uses network aggregation. We train dataset-specific networks together with an aggregation network in a unified framework. The loss function includes two main components: a task-specific loss (such as cross-entropy) and an aggregation loss. The proposed aggregation loss allows our model to learn how trained deep network parameters can be aggregated with an aggregation operator. We demonstrate that the proposed approach learns model aggregation at test time without any further training step, reducing the burden of transfer learning to a simple arithmetical operation. The proposed approach achieves comparable performance w.r.t. the baseline. Besides, if the aggregation operator has an inverse, we will show that our model also inherently allows for selective forgetting, i.e., the aggregated model can forget one of the datasets it was trained on, retaining information on the others.
    },
    author = {Bruno Casella and Alessio Chisari and Sebastiano Battiato and Mario Giuffrida.},
    editor = {Giovanni Maria Farinella and Petia Radeva and Kadi Bouatouch},
    title = {Transfer Learning via Test-time Neural Networks Aggregation},
    booktitle = {Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, {VISIGRAPP} 2022, Volume 5: VISAPP, Online Streaming, February 6-8, 2022},
    year = {2022},
    pages = {642-649},
    publisher = {SciTePress},
    organization = {INSTICC},
    doi = {10.5220/0010907900003124},
    isbn = {978-989-758-555-5},
    url = {https://iris.unito.it/retrieve/handle/2318/1844159/947123/TRANSFER_LEARNING_VIA_TEST_TIME_NEURAL_NETWORKS_AGGREGATION.pdf}
    }