SAILab

Filippo Costanti When: Oct 12th, 2022 – 11:45 – 12:30 AM Where: Google meet link Description Lifelong Learning of Graph Neural Networks for Open-World Node Classification Graph neural networks (GNNs) have emerged as the standard method for numerous tasks on graph-structured data such as node classification. However, real-world graphs are often evolving over time and […]

Barbara Toniella Corradini When: Oct 12th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description A Deep Learning approach for oocytes segmentation and analysis Medical Assisted Procreation (MAP) has seen a sharp increase in demand over the past decade, due to a variety of reasons, including genetic factors, health conditions altered by stress […]

Michele Casoni When: Sep 28th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Continual Learning: an Optimal Control approach Continual Learning is a branch of Machine Learning which studies the ability of a model to learn continually from a stream of data. For academics and practitioners, this new way of conceiving learning […]

Elia Giuseppe Ceroni When: Sep 21st, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Deep learning for the prediction of early on-treatment response in metastatic colorectal cancer from serial medical imaging by Lin Lu, Laurent Dercle, Binsheng Zhao, and Lawrence H. Schwartz In current clinical practice, tumor response assessment is usually based […]

Caterina Graziani When: Sep 14th, 2022 – 11:45 – 12:30 AM Where: Google meet link Description On the Extension of the Weisfeiler-Lehman Hierarchy by WL Tests for Arbitrary Graphs Graph isomorphism (GI) has occupied both theoreticians and applied scientists since the early 1950s. Over the years, several approaches and algorithms with which an isomorphism between […]

Veronica Lachi When: Sep 14th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Weisfeiler-Lehman goes dynamic: an analysis of the expressive power of Graph Neural Network for Attributed and Dynamic Graphs Graph Neural Networks (GNNs) are a large class of connectionist models for graph processing. Recent theoretical studies on the expressive power […]

Simone Marullo When: Jun 29th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Learning to Prompt for Continual Learning The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known […]

Giuseppe Alessio D’Inverno (University of Siena) When: Jun 8th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description 1-Lipschitz Neural Networks: a splines-based approach Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better […]

Lapo Faggi (University of Siena) When: Jun 1st, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Neural dynamic in temporal environments Learning in a continual manner is one of the main challenges that the machine learning community is currently facing. The importance of the problem can be readily understood as soon as […]

Enrico Meloni (University of Siena) When: May 25th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Pipeline Parallelism for Real-time Online Learning Deep Learning research has seen an ongoing increase in model complexity. It has been shown that scaling up network capacity is often an effective approach to enhance the performances of […]