36 citations · 149 across the 21 of their papers we have counts for
25 papers
Grounding Methods for Neural-Symbolic AI
Rodrigo Castellano Ontiveros, Francesco Giannini, Marco Gori +2
A large class of Neural-Symbolic (NeSy) methods employs a machine learner to process the input entities, while relying on a reasoner based on First-Order Logic to represent and pro…
Relational Concept Bottleneck Models
Pietro Barbiero, Francesco Giannini, Gabriele Ciravegna +2
The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs…
Interpretable Neural-Symbolic Concept Reasoning
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini +7
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning…
Enhancing Embedding Representations of Biomedical Data using Logic Knowledge
Michelangelo Diligenti, Francesco Giannini, Stefano Fioravanti +3
Knowledge Graph Embeddings (KGE) have become a quite popular class of models specifically devised to deal with ontologies and graph structure data, as they can implicitly encode st…
Neural Probabilistic Logic Programming in Discrete-Continuous Domains
Lennert De Smet, Pedro Zuidberg Dos Martires, Robin Manhaeve +3
Neural-symbolic AI (NeSy) allows neural networks to exploit symbolic background knowledge in the form of logic. It has been shown to aid learning in the limited data regime and to…
Safe Reinforcement Learning via Probabilistic Logic Shields
Wen-Chi Yang, Giuseppe Marra, Gavin Rens +1
Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to…
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna +9
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworth…
VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming
Eleonora Misino, Giuseppe Marra, Emanuele Sansone
We present VAEL, a neuro-symbolic generative model integrating variational autoencoders (VAE) with the reasoning capabilities of probabilistic logic (L) programming. Besides standa…
DeepStochLog: Neural Stochastic Logic Programming
Thomas Winters, Giuseppe Marra, Robin Manhaeve +1
Recent advances in neural symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic progr…
Relational Reasoning Networks
Giuseppe Marra, Michelangelo Diligenti, Francesco Giannini
Neuro-symbolic methods integrate neural architectures, knowledge representation and reasoning. However, they have been struggling at both dealing with the intrinsic uncertainty of…
Online Learning of Non-Markovian Reward Models
Gavin Rens, Jean-François Raskin, Raphaël Reynouad +1
There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks, that is, rewards are non-Markovian. One natural and quite g…
Deep Constraint-based Propagation in Graph Neural Networks
Matteo Tiezzi, Giuseppe Marra, Stefano Melacci +1
The popularity of deep learning techniques renewed the interest in neural architectures able to process complex structures that can be represented using graphs, inspired by Graph N…
Relational Neural Machines
Giuseppe Marra, Michelangelo Diligenti, Francesco Giannini +2
Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available. However, deep learning solely focuses on the accurac…
Local Propagation in Constraint-based Neural Network
Giuseppe Marra, Matteo Tiezzi, Stefano Melacci +3
In this paper we study a constraint-based representation of neural network architectures. We cast the learning problem in the Lagrangian framework and we investigate a simple optim…
A Lagrangian Approach to Information Propagation in Graph Neural Networks
Matteo Tiezzi, Giuseppe Marra, Stefano Melacci +2
In many real world applications, data are characterized by a complex structure, that can be naturally encoded as a graph. In the last years, the popularity of deep learning techniq…
Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances
Marco Maggini, Giuseppe Marra, Stefano Melacci +1
We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that…
An Unsupervised Character-Aware Neural Approach to Word and Context Representation Learning
Giuseppe Marra, Andrea Zugarini, Stefano Melacci +1
In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, a…
On the relation between Loss Functions and T-Norms
Francesco Giannini, Giuseppe Marra, Michelangelo Diligenti +2
Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the devel…
T-Norms Driven Loss Functions for Machine Learning
Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti +2
Neural-symbolic approaches have recently gained popularity to inject prior knowledge into a learner without requiring it to induce this knowledge from data. These approaches can po…
Neural Markov Logic Networks
Giuseppe Marra, Ondřej Kuželka
We introduce neural Markov logic networks (NMLNs), a statistical relational learning system that borrows ideas from Markov logic. Like Markov logic networks (MLNs), NMLNs are an ex…
LYRICS: a General Interface Layer to Integrate Logic Inference and Deep Learning
Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti +1
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some ki…
Integrating Learning and Reasoning with Deep Logic Models
Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti +1
Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic l…
Backpropagation and Biological Plausibility
Alessandro Betti, Marco Gori, Giuseppe Marra
By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent adv…
Constraint-Based Visual Generation
Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti +1
In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive explor…