arXiv subjects

Francesco Ricci

Publications and source records attributed to Francesco Ricci.

At least 19 recordsLinked to original sources

arXiv2026

Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support

More than twenty-five years ago, first ideas were developed on how to design a system that can provide recommendations to groups of users instead of individual users. Since then, a rich variety of algorithmic proposals were published, e.g., on how to acquire individual preferences, how to aggregate them, and how to generate recommendations for groups of users. However, despite the rich literature on the topic, barely any examples of real-world group recommender systems can be found. This lets us question common assumptions in academic research, in particular regarding communication processes in a group and how recommendation-supported decisions are made. In this essay, we argue that these common assumptions and corresponding system designs often may not match the needs or expectations of users. We thus call for a reorientation in this research area, leveraging the capabilities of modern Generative AI assistants like ChatGPT. Specifically, as one promising future direction, we envision group recommender systems to be systems where human group members interact in a chat and an AI-based group recommendation agent assists the decision-making process in an agentic way. Ultimately, this shall lead to a more natural group decision-making environment and finally to wider adoption of group recommendation systems in practice.

cs.IR↗

arXiv2025

High-throughput computation of electric polarization in solids via Berry flux diagonalization

Electric polarization in the absence of an externally applied electric field is a key property of polar materials, but the standard interpolation-based ab initio approach to compute polarization differences within the modern theory of polarization presents challenges for automated high-throughput calculations. Berry flux diagonalization [J. Bonini et. al, Phys. Rev. B 102, 045141 (2020)] has been proposed as an efficient and reliable alternative, though it has yet to be widely deployed. Here, we assess Berry flux diagonalization using ab initio calculations of a large set of materials, introducing and validating heuristics that ensure branch alignment with a minimal number of intermediate interpolated structures. Our automated implementation of Berry flux diagonalization succeeds in cases where prior interpolation-based workflows fail due to band-gap closures or branch ambiguities. Benchmarking with ab initio calculations of 176 candidate ferroelectrics, we demonstrate the efficacy of the approach on a broad range of insulating materials and obtain accurate effective polarization values with fewer interpolated structures than prior automated interpolation-based workflows. Our real-space heuristics that can predict gauge stability a priori from ionic displacements enable a general automated framework for reliable polarization calculations and efficient high-throughput screening of chemically and structurally diverse polar insulators. These results establish Berry flux diagonalization as a robust and efficient method to compute the effective polarization of solids and to accelerate the data-driven discovery of functional polar materials.

cond-mat.mtrl-sci↗

arXiv2025

Automated Workflow for Non-Empirical Wannier-Localized Optimal Tuning of Range-Separated Hybrid Functionals

We introduce an automated workflow for generating non-empirical Wannier-localized optimally-tuned screened range-separated hybrid (WOT-SRSH) functionals. WOT-SRSH functionals have been shown to yield highly accurate fundamental band gaps, band structures, and optical spectra for bulk and 2D semiconductors and insulators. Our workflow automatically and efficiently determines the WOT-SRSH functional parameters for a given crystal structure and composition, approximately enforcing the correct screened long-range Coulomb interaction and an ionization potential ansatz. In contrast to previous manual tuning approaches, our tuning procedure relies on a new search algorithm that only requires a few hybrid functional calculations with minimal user input. We demonstrate our workflow on 23 previously studied semiconductors and insulators, reporting the same high level of accuracy. By automating the tuning process and improving its computational efficiency, the approach outlined here enables applications of the WOT-SRSH functional to compute spectroscopic and optoelectronic properties for a wide range of materials.

cond-mat.mtrl-sci↗

arXiv2025

Point of Interest Recommendation: Pitfalls and Viable Solutions

Point of interest (POI) recommendation can play a pivotal role in enriching tourists' experiences by suggesting context-dependent and preference-matching locations and activities, such as restaurants, landmarks, itineraries, and cultural attractions. Unlike some more common recommendation domains (e.g., music and video), POI recommendation is inherently high-stakes: users invest significant time, money, and effort to search, choose, and consume these suggested POIs. Despite the numerous research works in the area, several fundamental issues remain unresolved, hindering the real-world applicability of the proposed approaches. In this paper, we discuss the current status of the POI recommendation problem and the main challenges we have identified. The first contribution of this paper is a critical assessment of the current state of POI recommendation research and the identification of key shortcomings across three main dimensions: datasets, algorithms, and evaluation methodologies. We highlight persistent issues such as the lack of standardized benchmark datasets, flawed assumptions in the problem definition and model design, and inadequate treatment of biases in the user behavior and system performance. The second contribution is a structured research agenda that, starting from the identified issues, introduces important directions for future work related to multistakeholder design, context awareness, data collection, trustworthiness, novel interactions, and real-world evaluation.

cs.IR↗

arXiv2025

Abinit 2025: New Capabilities for the Predictive Modeling of Solids and Nanomaterials

Abinit is a widely used scientific software package implementing density functional theory and many related functionalities for excited states and response properties. This paper presents the novel features and capabilities, both technical and scientific, which have been implemented over the past 5 years. This evolution occurred in the context of evolving hardware platforms, high-throughput calculation campaigns, and the growing use of machine learning to predict properties based on databases of first principles results. We present new methodologies for ground states with constrained charge, spin or temperature; for density functional perturbation theory extensions to flexoelectricity and polarons; and for excited states in many-body frameworks including GW, dynamical mean field theory, and coupled cluster. Technical advances have extended abinit high-performance execution to graphical processing units and intensive parallelism. Second principles methods build effective models on top of first principles results to scale up in length and time scales. Finally, workflows have been developed in different community frameworks to automate \abinit calculations and enable users to simulate hundreds or thousands of materials in controlled and reproducible conditions.

cond-mat.mtrl-sci↗

arXiv2025

Large Language Model Driven Recommendation

While previous chapters focused on recommendation systems (RSs) based on standardized, non-verbal user feedback such as purchases, views, and clicks -- the advent of LLMs has unlocked the use of natural language (NL) interactions for recommendation. This chapter discusses how LLMs' abilities for general NL reasoning present novel opportunities to build highly personalized RSs -- which can effectively connect nuanced and diverse user preferences to items, potentially via interactive dialogues. To begin this discussion, we first present a taxonomy of the key data sources for language-driven recommendation, covering item descriptions, user-system interactions, and user profiles. We then proceed to fundamental techniques for LLM recommendation, reviewing the use of encoder-only and autoregressive LLM recommendation in both tuned and untuned settings. Afterwards, we move to multi-module recommendation architectures in which LLMs interact with components such as retrievers and RSs in multi-stage pipelines. This brings us to architectures for conversational recommender systems (CRSs), in which LLMs facilitate multi-turn dialogues where each turn presents an opportunity not only to make recommendations, but also to engage with the user in interactive preference elicitation, critiquing, and question-answering.

cs.AI↗

arXiv2025

The reliability of hybrid functionals for accurate fundamental and optical gap prediction of bulk solids and surfaces

Hybrid functionals have been considered insufficiently reliable for the prediction of band gaps in solids and surfaces. We revisit this issue with a new generation of optimally-tuned range-separated hybrid functionals, focusing on the reconstructed Si(111)-(2x1) and Ge(111)-(2x1) surfaces. We show that certain hybrid functionals can accurately predict the surface-state and bulk fundamental and optical gaps, as well as projected band structures of these surfaces, by combining ground-state and time-dependent density functional theory.

cond-mat.mtrl-sci↗

arXiv2025

Widening the Role of Group Recommender Systems with CAJO

Group Recommender Systems (GRSs) have been studied and developed for more than twenty years. However, their application and usage has not grown. They can even be labeled as failures, if compared to the very successful and common recommender systems (RSs) used on all the major ecommerce and social platforms. As a result, the RSs that we all use now, are only targeted for individual users, aiming at choosing an item exclusively for themselves; no choice support is provided to groups trying to select a service, a product, an experience, a person, serving equally well all the group members. In this opinion article we discuss why the success of group recommender systems is lagging and we propose a research program unfolding on the analysis and development of new forms of collaboration between humans and intelligent systems. We define a set of roles, named CAJO, that GRSs should play in order to become more useful tools for group decision making.

cs.IR↗

arXiv2025

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research.

cs.LG↗

arXiv2024

Recommendation with Generative Models

Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions. In recent years, these models have gained prominence in machine learning due to the development of approaches such as generative adversarial networks (GANs), variational autoencoders (VAEs), and transformer-based architectures such as GPT. These models have applications across various domains, such as image generation, text synthesis, and music composition. In recommender systems, generative models, referred to as Gen-RecSys, improve the accuracy and diversity of recommendations by generating structured outputs, text-based interactions, and multimedia content. By leveraging these capabilities, Gen-RecSys can produce more personalized, engaging, and dynamic user experiences, expanding the role of AI in eCommerce, media, and beyond. Our book goes beyond existing literature by offering a comprehensive understanding of generative models and their applications, with a special focus on deep generative models (DGMs) and their classification. We introduce a taxonomy that categorizes DGMs into three types: ID-driven models, large language models (LLMs), and multimodal models. Each category addresses unique technical and architectural advancements within its respective research area. This taxonomy allows researchers to easily navigate developments in Gen-RecSys across domains such as conversational AI and multimodal content generation. Additionally, we examine the impact and potential risks of generative models, emphasizing the importance of robust evaluation frameworks.

cs.IR↗

arXiv2024

Multi-modal Generative Models in Recommendation System

Many recommendation systems limit user inputs to text strings or behavior signals such as clicks and purchases, and system outputs to a list of products sorted by relevance. With the advent of generative AI, users have come to expect richer levels of interactions. In visual search, for example, a user may provide a picture of their desired product along with a natural language modification of the content of the picture (e.g., a dress like the one shown in the picture but in red color). Moreover, users may want to better understand the recommendations they receive by visualizing how the product fits their use case, e.g., with a representation of how a garment might look on them, or how a furniture item might look in their room. Such advanced levels of interaction require recommendation systems that are able to discover both shared and complementary information about the product across modalities, and visualize the product in a realistic and informative way. However, existing systems often treat multiple modalities independently: text search is usually done by comparing the user query to product titles and descriptions, while visual search is typically done by comparing an image provided by the customer to product images. We argue that future recommendation systems will benefit from a multi-modal understanding of the products that leverages the rich information retailers have about both customers and products to come up with the best recommendations. In this chapter we review recommendation systems that use multiple data modalities simultaneously.

cs.IR↗

arXiv2024

Predicting Group Choices from Group Profiles

Group recommender systems (GRSs) identify items to recommend to a group of people by aggregating group members' individual preferences into a group profile, and selecting the items that have the largest score in the group profile. The GRS predicts that these recommendations would be chosen by the group, by assuming that the group is applying the same preference aggregation strategy as the one adopted by the GRS. However, predicting the choice of a group is more complex since the GRS is not aware of the exact preference aggregation strategy that is going to be used by the group. To this end, the aim of this paper is to validate the research hypothesis that, by using a machine learning approach and a data set of observed group choices, it is possible to predict a group's final choice, better than by using a standard preference aggregation strategy. Inspired by the Decision Scheme theory, which first tried to address the group choice prediction problem, we search for a group profile definition that, in conjunction with a machine learning model, can be used to accurately predict a group choice. Moreover, to cope with the data scarcity problem, we propose two data augmentation methods, which add synthetic group profiles to the training data, and we hypothesize they can further improve the choice prediction accuracy. We validate our research hypotheses by using a data set containing 282 participants organized in 79 groups. The experiments indicate that the proposed method outperforms baseline aggregation strategies when used for group choice prediction. The method we propose is robust with the presence of missing preference data and achieves a performance superior to what humans can achieve on the group choice prediction task. Finally, the proposed data augmentation method can also improve the prediction accuracy.

cs.IR↗

arXiv2023

Trustworthy Recommender Systems

Recommender systems (RSs) aim to help users to effectively retrieve items of their interests from a large catalogue. For a quite long period of time, researchers and practitioners have been focusing on developing accurate RSs. Recent years have witnessed an increasing number of threats to RSs, coming from attacks, system and user generated noise, system bias. As a result, it has become clear that a strict focus on RS accuracy is limited and the research must consider other important factors, e.g., trustworthiness. For end users, a trustworthy RS (TRS) should not only be accurate, but also transparent, unbiased and fair as well as robust to noise or attacks. These observations actually led to a paradigm shift of the research on RSs: from accuracy-oriented RSs to TRSs. However, researchers lack a systematic overview and discussion of the literature in this novel and fast developing field of TRSs. To this end, in this paper, we provide an overview of TRSs, including a discussion of the motivation and basic concepts of TRSs, a presentation of the challenges in building TRSs, and a perspective on the future directions in this area. We also provide a novel conceptual framework to support the construction of TRSs.

cs.IR↗

arXiv2023

Outcome-Oriented Prescriptive Process Monitoring Based on Temporal Logic Patterns

Prescriptive Process Monitoring systems recommend, during the execution of a business process, interventions that, if followed, prevent a negative outcome of the process. Such interventions have to be reliable, that is, they have to guarantee the achievement of the desired outcome or performance, and they have to be flexible, that is, they have to avoid overturning the normal process execution or forcing the execution of a given activity. Most of the existing Prescriptive Process Monitoring solutions, however, while performing well in terms of recommendation reliability, provide the users with very specific (sequences of) activities that have to be executed without caring about the feasibility of these recommendations. In order to face this issue, we propose a new Outcome-Oriented Prescriptive Process Monitoring system recommending temporal relations between activities that have to be guaranteed during the process execution in order to achieve a desired outcome. This softens the mandatory execution of an activity at a given point in time, thus leaving more freedom to the user in deciding the interventions to put in place. Our approach defines these temporal relations with Linear Temporal Logic over finite traces patterns that are used as features to describe the historical process data recorded in an event log by the information systems supporting the execution of the process. Such encoded log is used to train a Machine Learning classifier to learn a mapping between the temporal patterns and the outcome of a process execution. The classifier is then queried at runtime to return as recommendations the most salient temporal patterns to be satisfied to maximize the likelihood of a certain outcome for an input ongoing process execution. The proposed system is assessed using a pool of 22 real-life event logs that have already been used as a benchmark in the Process Mining community.

cs.AI↗

arXiv2022

Learning to act: a Reinforcement Learning approach to recommend the best next activities

The rise of process data availability has recently led to the development of data-driven learning approaches. However, most of these approaches restrict the use of the learned model to predict the future of ongoing process executions. The goal of this paper is moving a step forward and leveraging available data to learning to act, by supporting users with recommendations derived from an optimal strategy (measure of performance). We take the optimization perspective of one process actor and we recommend the best activities to execute next, in response to what happens in a complex external environment, where there is no control on exogenous factors. To this aim, we investigate an approach that learns, by means of Reinforcement Learning, the optimal policy from the observation of past executions and recommends the best activities to carry on for optimizing a Key Performance Indicator of interest. The validity of the approach is demonstrated on two scenarios taken from real-life data.

cs.AI↗

arXiv2022

A chemical nano-reactor based on a levitated nanoparticle in vacuum

A single levitated nanoparticle is used as a nano-reactor for studying surface chemistry at the nanoscale. Optical levitation under controlled pressure, surrounding gas composition, and humidity provides extreme control over the nanoparticle, including dynamics, charge, and surface chemistry. Using a single nanoparticle avoids ensemble averages and allows to study how the presence of silanol groups at its surface affects the adsorption and desorption of water from the background gas with unprecedented real time, spatial, and temporal resolution. Here, we demonstrate the unique potential of this versatile platform by studying the Zhuravlev model in silica particles. In contrast to standard methods, our system allowed the first observation of an abrupt and irreversible change in scattering cross section, mass, and mechanical eigenfrequency during the dehydroxylation process, indicating changes in density, refractive index and volume.

physics.chem-ph↗

arXiv2022

Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings

Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.

cond-mat.mtrl-sci↗

arXiv2021

Giant thermoelectric figure of merit in multivalley high-complexity-factor LaSO

We report a giant thermoelectric figure of merit $ZT$ (up to 6 at 1100 K) in $n$-doped lanthanum oxysulphate LaSO. Thermoelectric coefficients are computed from ab initio bands within Bloch-Boltzmann theory in an energy-, chemical potential- and temperature-dependent relaxation time approximation. The lattice thermal conductivity is estimated from a model employing the ab initio phonon and Grüneisen-parameter spectrum. The main source of the large $ZT$ is the significant power factor which correlates with a large band complexity factor. We also suggest a possible $n$-type dopant for the material based on ab initio calculations.

cond-mat.mtrl-sci↗