← Search

Michelangelo Diligenti

7 accepted papers

2026

DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs

AAAI 2026technical

Neurosymbolic (NeSy) AI combines neural architectures and symbolic reasoning to improve accuracy, interpretability, and generalization. While logic inference on top of subsymbolic modules has been shown to effectively guarantee these properties, this often comes at the cost of reduced scalability, w

Cited by 0SourcePDFScholar
2026

Mixture of Concept Bottleneck Experts

ICML 2026spotlight

Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propos…

Cited by 0SourceScholar
2025

Grounding Methods for Neural-Symbolic AI

IJCAI 2025

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 process more complex relationships among the entities. A fundamental role for these methods is played by the process of log

2024

Interpretable Concept-Based Memory Reasoning

NeurIPS 2024poster

The lack of transparency in the decision-making processes of deep learning systems presents a significant challenge in modern artificial intelligence (AI), as it impairs users’ ability to rely on and verify these systems. To address this challenge, Concept Bottleneck Models (CBMs) have made signific…

2024

Relational Concept Bottleneck Models

NeurIPS 2024poster

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), are not designed to solve relational problems, while relational deep learning models, such as Graph Neural Networks (…

2022

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

NeurIPS 2022accept

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an intermediate level of human-like concepts. This enables human intervent…

2021

Contrastive Losses and Solution Caching for Predict-and-Optimize

IJCAI 2021poster

Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class have been successfully addressed via end-to-end learning approaches, which rely on solving one optimization problem for…