Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Polato, Mirko"'
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are
Externí odkaz:
http://arxiv.org/abs/2404.01039
Autor:
Mittone, Gianluca, Tonci, Nicolò, Birke, Robert, Colonnelli, Iacopo, Medić, Doriana, Bartolini, Andrea, Esposito, Roberto, Parisi, Emanuele, Beneventi, Francesco, Polato, Mirko, Torquati, Massimo, Benini, Luca, Aldinucci, Marco
Publikováno v:
In Proceedings of the 20th ACM International Conference on Computing Frontiers 2023 (CF '23), ACM, New York, NY, USA, 73-83
Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) are starting to flourish, many are not fle
Externí odkaz:
http://arxiv.org/abs/2302.07946
The recent rise in deep learning technologies fueled innovation and boosted scientific research. Their achievements enabled new research directions for deep generative modeling (DGM), an increasingly popular approach that can create novel and unseen
Externí odkaz:
http://arxiv.org/abs/2204.12577
Interpretability is having an increasingly important role in the design of machine learning algorithms. However, interpretable methods tend to be less accurate than their black-box counterparts. Among others, DNFs (Disjunctive Normal Forms) are argua
Externí odkaz:
http://arxiv.org/abs/2204.05251
In this paper, we propose a Conditioned Variational Autoencoder (C-VAE) for constrained top-N item recommendation where the recommended items must satisfy a given condition. The proposed model architecture is similar to a standard VAE in which the co
Externí odkaz:
http://arxiv.org/abs/2004.11141
Autor:
Polato, Mirko, Aiolli, Fabio
A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem is seen a
Externí odkaz:
http://arxiv.org/abs/1812.07895
Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business man
Externí odkaz:
http://arxiv.org/abs/1711.03822
Publikováno v:
In Neurocomputing 28 March 2022 479:106-120
Autor:
Polato, Mirko, Aiolli, Fabio
In many personalized recommendation problems available data consists only of positive interactions (implicit feedback) between users and items. This problem is also known as One-Class Collaborative Filtering (OC-CF). Linear models usually achieve sta
Externí odkaz:
http://arxiv.org/abs/1612.07025
Autor:
Polato, Mirko, Aiolli, Fabio
The increasing availability of implicit feedback datasets has raised the interest in developing effective collaborative filtering techniques able to deal asymmetrically with unambiguous positive feedback and ambiguous negative feedback. In this paper
Externí odkaz:
http://arxiv.org/abs/1612.05729