Search Results for author: Franco Scarselli

Found 14 papers, 3 papers with code

VC dimension of Graph Neural Networks with Pfaffian activation functions

1 code implementation22 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.

A topological description of loss surfaces based on Betti Numbers

no code implementations8 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.

SortNet: Learning To Rank By a Neural-Based Sorting Algorithm

no code implementations3 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.

Learning-To-Rank

Weisfeiler--Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs

no code implementations8 Oct 2022 Silvia Beddar-Wiesing, Giuseppe Alessio D'Inverno, Caterina Graziani, Veronica Lachi, Alice Moallemy-Oureh, Franco Scarselli, Josephine Maria Thomas

Then, the results on the expressive power of GNNs are extended by proving that GNNs have the same capability as the 1-WL test in distinguishing dynamic and attributed graphs, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence.

Modular multi-source prediction of drug side-effects with DruGNN

no code implementations15 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.

Drug Discovery

Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities

1 code implementation29 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).

Management Recommendation Systems

On the approximation capability of GNNs in node classification/regression tasks

1 code implementation16 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.

Clustering Graph Classification +2

Molecular graph generation with Graph Neural Networks

no code implementations14 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.

Drug Discovery Graph Generation +1

Embedding of FRPN in CNN architecture

no code implementations27 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.

Image Classification

Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation

no code implementations19 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.

Segmentation Text Segmentation +2

A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

no code implementations29 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.

Image-to-Image Translation Retinal Vessel Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.