no code implementations • 29 Mar 2024 • Barbara Toniella Corradini, Mustafa Shukor, Paul Couairon, Guillaume Couairon, Franco Scarselli, Matthieu Cord
The pipeline is as follows: the image is passed to both a captioner model (i. e. BLIP) and a diffusion model (i. e., Stable Diffusion Model) to generate a text description and visual representation, respectively.
1 code implementation • 22 Jan 2024 • Giuseppe Alessio D'Inverno, Monica Bianchini, Franco Scarselli
Graph Neural Networks (GNNs) have emerged in recent years as a powerful tool to learn tasks across a wide range of graph domains in a data-driven fashion; based on a message passing mechanism, GNNs have gained increasing popularity due to their intuitive formulation, closely linked with the Weisfeiler-Lehman (WL) test for graph isomorphism, to which they have proven equivalent.
no code implementations • 8 Jan 2024 • Maria Sofia Bucarelli, Giuseppe Alessio D'Inverno, Monica Bianchini, Franco Scarselli, Fabrizio Silvestri
In the context of deep learning models, attention has recently been paid to studying the surface of the loss function in order to better understand training with methods based on gradient descent.
no code implementations • 3 Nov 2023 • Leonardo Rigutini, Tiziano Papini, Marco Maggini, Franco Scarselli
Two main approaches exist in literature for the task of learning to rank: 1) a score function, learned by examples, which evaluates the properties of each object yielding an absolute relevance value that can be used to order the objects or 2) a pairwise approach, where a "preference function" is learned using pairs of objects to define which one has to be ranked first.
no code implementations • 2 Feb 2023 • Antonio Longa, Veronica Lachi, Gabriele Santin, Monica Bianchini, Bruno Lepri, Pietro Lio, Franco Scarselli, Andrea Passerini
Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data.
1 code implementation • 8 Oct 2022 • Silvia Beddar-Wiesing, Giuseppe Alessio D'Inverno, Caterina Graziani, Veronica Lachi, Alice Moallemy-Oureh, Franco Scarselli, Josephine Maria Thomas
In this paper, we conduct a theoretical analysis of the expressive power of GNNs for two other graph domains that are particularly interesting in practical applications, namely dynamic graphs and SAUGHs with edge attributes.
no code implementations • 15 Feb 2022 • Pietro Bongini, Franco Scarselli, Monica Bianchini, Giovanna Maria Dimitri, Niccolò Pancino, Pietro Liò
Drug Side-Effects (DSEs) have a high impact on public health, care system costs, and drug discovery processes.
1 code implementation • 29 Dec 2021 • José Suárez-Varela, Paul Almasan, Miquel Ferriol-Galmés, Krzysztof Rusek, Fabien Geyer, Xiangle Cheng, Xiang Shi, Shihan Xiao, Franco Scarselli, Albert Cabellos-Aparicio, Pere Barlet-Ros
Graph neural networks (GNN) have shown outstanding applications in many fields where data is fundamentally represented as graphs (e. g., chemistry, biology, recommendation systems).
1 code implementation • 16 Jun 2021 • Giuseppe Alessio D'Inverno, Monica Bianchini, Maria Lucia Sampoli, Franco Scarselli
Furthermore, all current results are dedicated to graph classification/regression tasks, where the GNN must produce a single output for the whole graph, while also node classification/regression problems, in which an output is returned for each node, are very common.
no code implementations • 9 Jun 2021 • Giorgio Ciano, Paolo Andreini, Tommaso Mazzierli, Monica Bianchini, Franco Scarselli
Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems.
no code implementations • 14 Dec 2020 • Pietro Bongini, Monica Bianchini, Franco Scarselli
The use of graph neural networks maximizes the information in input at each generative step, which consists of the subgraph produced during the previous steps.
no code implementations • 27 Dec 2019 • Alberto Rossi, Markus Hagenbuchner, Franco Scarselli, Ah Chung Tsoi
The unfolding realized with this kind of iterative mechanism allows to simulate a deep neural network with any number of layers.
no code implementations • 19 Nov 2019 • Simone Bonechi, Paolo Andreini, Monica Bianchini, Franco Scarselli
Providing pixel-level supervisions for scene text segmentation is inherently difficult and costly, so that only few small datasets are available for this task.
no code implementations • 29 Jul 2019 • Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Franco Scarselli, Andrea Sodi
In this paper, we use Generative Adversarial Networks (GANs) for synthesizing high quality retinal images, along with the corresponding semantic label-maps, to be used instead of real images during the training process.
no code implementations • 1 Apr 2019 • Simone Bonechi, Paolo Andreini, Monica Bianchini, Franco Scarselli
The generated annotations are used to train a deep convolutional neural network for semantic segmentation.