40.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of TrentoIT265 papers
- European Centre for Theoretical Studies in Nuclear Physics and Related AreasIT190 papers
- Istituto Nazionale di Fisica Nucleare, Trento Institute for Fundamental Physics And ApplicationsIT136 papers
- Centre National de la Recherche ScientifiqueFR99 papers
- Istituto Nazionale di Fisica NucleareIT74 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR61 papers
- Istituto di Fotonica e NanotecnologieIT59 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di GenovaIT52 papers
- University of PisaIT50 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di MilanoIT46 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma IIT46 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT45 papers
27 papers · 1 filter
Deep Learning for Crime Forecasting: The Role of Mobility at Fine-grained Spatiotemporal Scales
Ariadna Albors Zumel, Michele Tizzoni, Gian Maria Campedelli
Objectives: To develop a deep learning framework to evaluate if and how incorporating micro-level mobility features, alongside historical crime and sociodemographic data, enhances…
AI reconstruction of European weather from the Euro-Atlantic regimes
A. Camilletti, G. Franch, E. Tomasi +1
We present a non-linear AI-model designed to reconstruct monthly mean anomalies of the European temperature and precipitation based on the Euro-Atlantic Weather regimes (WR) indice…
Group-robust Machine Unlearning
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the d…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks
Mátyás Vincze, Laura Ferrarotti, Leonardo Lucio Custode +2
Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box po…
Time Can Invalidate Algorithmic Recourse
Giovanni De Toni, Stefano Teso, Bruno Lepri +1
Algorithmic Recourse (AR) aims to provide users with actionable steps to overturn unfavourable decisions made by machine learning predictors. However, these actions often take time…
Hopfield Networks for Asset Allocation
Carlo Nicolini, Monisha Gopalan, Jacopo Staiano +1
We present the first application of modern Hopfield networks to the problem of portfolio optimization. We performed an extensive study based on combinatorial purged cross-validatio…
GPTCast: a weather language model for precipitation nowcasting
Gabriele Franch, Elena Tomasi, Rishabh Wanjari +4
This work introduces GPTCast, a generative deep-learning method for ensemble nowcast of radar-based precipitation, inspired by advancements in large language models (LLMs). We empl…
Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0\_CLM9 simulations
Elena Tomasi, Gabriele Franch, Marco Cristoforetti
Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields…
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Antonio Longa, Steve Azzolin, Gabriele Santin +4
Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting…
Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions
Alessandro Daniele, Tommaso Campari, Sagar Malhotra +1
Neuro-Symbolic (NeSy) integration combines symbolic reasoning with Neural Networks (NNs) for tasks requiring perception and reasoning. Most NeSy systems rely on continuous relaxati…
Personalized Algorithmic Recourse with Preference Elicitation
Giovanni De Toni, Paolo Viappiani, Stefano Teso +2
Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the…
A Framework for Verifiable and Auditable Federated Anomaly Detection
Gabriele Santin, Inna Skarbovsky, Fabiana Fournier +1
Federated Leaning is an emerging approach to manage cooperation between a group of agents for the solution of Machine Learning tasks, with the goal of improving each agent's perfor…
Generating Synthetic Mobility Networks with Generative Adversarial Networks
Giovanni Mauro, Massimiliano Luca, Antonio Longa +2
The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the inter…
Posture Prediction for Healthy Sitting using a Smart Chair
Tariku Adane Gelaw, Misgina Tsighe Hagos
Poor sitting habits have been identified as a risk factor to musculoskeletal disorders and lower back pain especially on the elderly, disabled people, and office workers. In the cu…
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
Giovanni De Toni, Bruno Lepri, Andrea Passerini
Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unf…
Quantum field theories, Markov random fields and machine learning
Dimitrios Bachtis, Gert Aarts, Biagio Lucini
The transition to Euclidean space and the discretization of quantum field theories on spatial or space-time lattices opens up the opportunity to investigate probabilistic machine l…
Process discovery on deviant traces and other stranger things
Federico Chesani, Chiara Di Francescomarino, Chiara Ghidini +5
As the need to understand and formalise business processes into a model has grown over the last years, the process discovery research field has gained more and more importance, dev…
Machine learning with quantum field theories
Dimitrios Bachtis, Gert Aarts, Biagio Lucini
The precise equivalence between discretized Euclidean field theories and a certain class of probabilistic graphical models, namely the mathematical framework of Markov random field…
How do I update my model? On the resilience of Predictive Process Monitoring models to change
Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini +1
Existing well investigated Predictive Process Monitoring techniques typically construct a predictive model based on past process executions, and then use it to predict the future o…
Structured Deep Kernel Networks for Data-Driven Closure Terms of Turbulent Flows
Tizian Wenzel, Marius Kurz, Andrea Beck +2
Standard kernel methods for machine learning usually struggle when dealing with large datasets. We review a recently introduced Structured Deep Kernel Network (SDKN) approach that…
Kernel-Based Models for Influence Maximization on Graphs based on Gaussian Process Variance Minimization
Salvatore Cuomo, Wolfgang Erb, Gabriele Santin
The inference of novel knowledge, the discovery of hidden patterns, and the uncovering of insights from large amounts of data from a multitude of sources make Data Science (DS) to…
Detecting discriminatory risk through data annotation based on Bayesian inferences
Elena Beretta, Antonio Vetrò, Bruno Lepri +1
Thanks to the increasing growth of computational power and data availability, the research in machine learning has advanced with tremendous rapidity. Nowadays, the majority of auto…
Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices
Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli +3
Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in te…