Roberto Confalonieri

Roberto Confalonieri
University of Padua | UNIPD · Department of Mathematics

Ph.D AI

About

67
Publications
20,132
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,681
Citations
Additional affiliations
November 2014 - present
Spanish National Research Council
Position
  • PostDoc Position
November 2012 - August 2013
Goldsmiths University of London
Position
  • PostDoc Position
October 2011 - September 2012
Université Toulouse III - Paul Sabatier
Position
  • PostDoc Position

Publications

Publications (67)
Preprint
Full-text available
Decision trees are a popular machine learning method, known for their inherent explainability. In Explainable AI, decision trees can be used as surrogate models for complex black box AI models or as approximations of parts of such models. A key challenge of this approach is determining how accurately the extracted decision tree represents the origi...
Chapter
Multiuser museum interactives are computer systems installed in museums or galleries that allow several visitors to interact together with digital representations of artefacts and information from the museum’s collection. WeCurate is such a system that allows users to collaboratively create a virtual exhibition from a cultural image archive. It pro...
Article
Full-text available
There has been a renewed interest in symbolic AI in recent years. Symbolic AI is indeed one of the key enabling technologies for the development of neuro-symbolic AI systems, as it can mitigate the limited capabilities of black box deep learning models to perform reasoning and provide support for explanations. This paper discusses the different rol...
Article
Full-text available
Understanding black box models has become paramount as systems based on opaque Artificial Intelligence(AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its app...
Article
Full-text available
Hyperspectral images consist of a multitude of spectral bands for each pixel. Spectral bands provide information about wavelengths that may cover a larger spectrum of what the human eye may see. In the hyperspectral domain, the classification of hyperspectral images is usually addressed by taking into account only the spectral information. However,...
Preprint
Full-text available
This paper discusses the different roles that explicit knowledge, in particular ontologies, can play in Explainable AI and in the development of human-centric explainable systems and intelligible explanations. We consider three main perspectives in which ontologies can contribute significantly, namely reference modelling, common-sense reasoning, an...
Conference Paper
Full-text available
Prototype theories are an important family of cognitive theories of concepts that model the classification under a concept in terms of the proximity of an object to the prototype of the concept. While logic-based definitions of concepts are standard in Description Logics and OWL, prototype-based definitions are not directly available, although they...
Preprint
Full-text available
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements i...
Article
Full-text available
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model’s decision-making. Thus, the need for eXplainable AI (XAI) methods f...
Article
Full-text available
The assessment of explanations by humans presents a significant challenge within the context of Explainable and Trustworthy AI. This is attributed not only to the absence of universal metrics and standardized evaluation methods, but also to complexities tied to devising user studies that assess the perceived human comprehensibility of these explana...
Chapter
Weighted Threshold Operators are n-ary operators that compute a weighted sum of their arguments and verify whether it reaches a certain threshold. They have been extensively studied in the area of circuit complexity theory, as well as in the neural network community under the name of perceptrons. In Knowledge Representation, they have been introduc...
Chapter
Concept refinement operators have been introduced to describe and compute generalisations and specialisations of concepts, with, amongst others, applications in concept learning and ontology repair through axiom weakening. We here provide a probabilistic proof of almost-certain termination for iterated refinements, thus for an axiom weakening proce...
Chapter
Technology transfer is a complex and multifaceted activity whose main goal is to promote academic knowledge transfer from academia to industry. In this context, one of the most challenging parts of technology transfer activities is to inform stakeholders from the industry about the availability of academic results. Traditionally, this occurs throug...
Article
Full-text available
Since recommender systems play an important role in our online experience today and are involved in a wide range of decisions, multiple stakeholders are requesting explanations for the corresponding algorithmic predictions. These demands—together with the benefits of explanations (e.g., trust, efficiency, and sometimes even persuasion)—have trigger...
Chapter
The lack of attention to sex and gender biases in biomedicine and healthcare hinders the advancement toward Precision Medicine. This chapter introduces a unified framework that captures the main steps that AI stakeholders need to go through in order to deal with desired and undesired sex and gender biases in AI models used for biomedical research a...
Conference Paper
Full-text available
We introduce a novel framework to deal with fairness, accountability and explainability of intelligent systems. This framework puts together several tools to deal with bias at the level of data, algorithms and human cognition. The framework makes use of intelligent classifiers endowed with fuzzy-grounded linguistic explainability. As a result, it f...
Article
Full-text available
The interest in explainable artificial intelligence has grown strongly in recent years because of the need to convey safety and trust in the ‘how’ and ‘why’ of automated decision-making to users. While a plethora of approaches has been developed, only a few focus on how to use domain knowledge and how this influences the understanding of explanatio...
Article
Full-text available
Explainability in Artificial Intelligence (AI) has been revived as a topic of active research by the need of conveying safety and trust to users in the “how” and “why” of automated decision‐making in different applications such as autonomous driving, medical diagnosis, or banking and finance. While explainability in AI has recently received signifi...
Article
Full-text available
The cognitive-linguistic theory of conceptual blending was introduced by Fauconnier and Turner in the late 90s to provide a descriptive model and foundational approach for the (almost uniquely) human ability to invent new concepts. Whilst blending is often described as ‘fluid’ and ‘effortless’ when ascribed to humans, it becomes a highly complex, m...
Article
Full-text available
Explainability is assumed to be a key factor for the adoption of Artificial Intelligence systems in a wide range of contexts. The use of AI components in self-driving cars, medical diagnosis, or insurance and financial services has shown that when decisions are taken or suggested by automated systems it is essential for practical, social, and legal...
Preprint
Full-text available
Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the `how' and `why' of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the...
Conference Paper
Full-text available
Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the 'how' and 'why' of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the...
Conference Paper
Full-text available
Axiom weakening is a novel technique that allows for fine-grained repair of inconsistent ontologies. In a multi-agent setting, integrating ontologies corresponding to multiple agents may lead to inconsistencies. Such inconsistencies can be resolved after the integrated ontology has been built, or their generation can be prevented during ontology ge...
Chapter
In this chapter, we present a computational framework that models concept invention. The framework is based on and extends conceptual blending. Apart from the blending mechanism modeling the creation of new concepts, the framework considers two extra dimensions, namely, origin and destination. For the former, we describe how a Rich Background suppo...
Chapter
The goal of the COINVENT project was not only to develop a novel, computationally feasible, formal model of conceptual blending that was sufficiently precise for capturing the fundamental insights of Fauconnier and Turner’s theory, but also to implement a creative computational system based on this novel formal model. In this chapter, we overview C...
Book
This book introduces a computationally feasible, cognitively inspired formal model of concept invention, drawing on Fauconnier and Turner's theory of conceptual blending, a fundamental cognitive operation. The chapters present the mathematical and computational foundations of concept invention, discuss cognitive and social aspects, and further desc...
Article
Full-text available
We present a computational framework for conceptual blending, a concept invention method that is advocated in cognitive science as a fundamental and uniquely human engine for creative thinking. Our framework treats a crucial part of the blending process, namely the generalisation of input concepts, as a search problem that is solved by means of mod...
Article
Full-text available
Ontology engineering is a hard and error-prone task, in which small changes may lead to errors, or even produce an inconsistent ontology. As ontologies grow in size, the need for automated methods for repairing inconsistencies while preserving as much of the original knowledge as possible increases. Most previous approaches to this task are based o...
Preprint
Ontology engineering is a hard and error-prone task, in which small changes may lead to errors, or even produce an inconsistent ontology. As ontologies grow in size, the need for automated methods for repairing inconsistencies while preserving as much of the original knowledge as possible increases. Most previous approaches to this task are based o...
Conference Paper
Full-text available
Ontologies represent principled, formalised descriptions of agents' conceptualisations of a domain. For a community of agents, these descriptions may differ among agents. We propose an aggregative view of the integration of ontologies based on Judgement Aggregation (JA). Agents may vote on statements of the ontologies, and we aim at constructing a...
Conference Paper
Full-text available
We address the problem of analysing the joint coherence of a number of concepts with respect to a background ontology. To address this problem, we explore the applicability of Paul Thagard's computational theory of coherence, in combination with semantic similarity between concepts based on a generalisation operator. In particular, given the input...
Article
Full-text available
Studying the prediction of new links in evolutionary networks is a captivating question that has received the interest of different disciplines. Link prediction allows to extract missing information and evaluate network dynamics. Some algorithms that tackle this problem with good performances are based on the sociability index, a measure of node in...
Article
Conceptual blending is a mental process that serves a variety of cognitive purposes, including human creativity. In this line of thinking, human creativity is modeled as a process that takes different mental spaces as input and combines them into a new mental space, called a blend. According to this form of combinational creativity, a blend is cons...
Conference Paper
Full-text available
Conceptual blending is a powerful tool for computational creativity where, for example, the properties of two harmonic spaces may be combined in a consistent manner to produce a novel harmonic space. However, deciding about the importance of property features in the input spaces and evaluating the results of conceptual blending is a nontrivial task...
Conference Paper
Full-text available
We present a framework for conceptual blending – a concept invention method that is advocated in cognitive science as a fundamental, and uniquely human engine for creative thinking. Herein, we employ the search capabilities of ASP to find commonalities among input concepts as part of the blending process , and we show how our approach fits within a...
Conference Paper
Full-text available
We present a computational framework for chord invention based on a cognitive-theoretic perspective on conceptual blending. The framework builds on algebraic specifications, and solves two musicological problems. It automatically finds transitions between chord progressions of different keys or idioms, and it substitutes chords in a chord progressi...
Conference Paper
Full-text available
This paper proposes the notion of experience to help situate agents in their environment, providing a link on how the continually evolving environment impacts the evolution of an agent's BDI model and vice versa. Then, using the notion of shared experience as a primitive construct, we develop a novel formal model of shared intention which we believ...
Conference Paper
Full-text available
Multiuser museum interactives are computer systems installed in museums or galleries which allow several visitors to interact together with digital representations of artefacts and information from the museum's collection. WeCurate is such a system, providing a multiuser curation workflow where the aim is for the users to synchronously view and dis...
Conference Paper
WeCurate is a multiuser museum interactive system that allows users to collaboratively create a virtual exhibition from a cultural image archive. WeCurate provides a synchronised image browser across multiple devices to enable a group of users to work together to curate a collection of images, through negotiation and collective decision making. Thi...
Article
A qualitative approach to decision making under uncertainty has been proposed in the setting of possibility theory, which is based on the assumption that levels of certainty and levels of priority (for expressing preferences) are commensurate. In this setting, pessimistic and optimistic decision criteria have been formally justified. This approach...
Conference Paper
Full-text available
This paper proposes a system that allows a group of human users to share their cultural experiences online, like buying together a gift from a museum or browsing simultaneously the collection of this museum. We show that such application involves two multiple criteria decision problems for choosing between different alternatives (e.g. possible gift...
Chapter
Full-text available
In context-aware systems, the representation of user profiles can greatly enhance the users' experience. User profiles often requires a compact and, at the same time, expressive language in order to represent conditional preferences, preference relations over the items they contain, and uncertainty labels. This paper presents the use of a possibili...
Conference Paper
The representation of preference queries to an uncertain data-base requires a framework capable of dealing with preferences and uncertainty in a separate way. Possibilistic logic has shown to be a suitable setting to support different kinds of preference queries. In this paper, we propose a counterpart of the possibilistic logic-based preference qu...
Article
In this paper, we show how the formalism of Logic Programs with Ordered Disjunction (LPODs) and Possibilistic Answer Set Programming (PASP) can be merged into the single framework of Logic Programs with Possibilistic Ordered Disjunction (LPPODs). The LPPODs framework embeds in a unified way several aspects of common-sense reasoning, nonmonotonocity...
Conference Paper
Full-text available
This paper presents a multi-stage ontology-based touristic recommender system which offers: personalized suggestions to citizens and tourists, including those with special needs; and information concerning the suggested locations. The system's suggestions are based on user profiles which are continuously updated via feedback obtained from past inte...
Conference Paper
Full-text available
We introduce the new concept of community browsing: A group of people browsing the web together and simultaneously. Community browsing is part of the broader notion of shared experience, where individuals share the experience of an event. We have developed a prototype of a mobile application that enables community browsing, and involves new technol...
Article
Full-text available
WeCurate is a shared image browser for collaboratively curating a virtual exhibition from a cultural image archive. This paper is concerned with the evaluation and iteration of a prototype UI (User In- Terface) design to enable this community image browsing. In WeCurate, several remote users work together with autonomic agents to browse the archive...
Conference Paper
Default rules, i.e. statements of the form normally a’s are b’s, are usually handled in Answer Set Programming by means of negation as failure which provides a way to capture exceptions to normal situations. In this paper we propose another approach which offers an operational counterpart to negation as failure, and which may be thought as a corres...
Conference Paper
Full-text available
Possibility theory offers a qualitative framework for modeling decision under uncertainty. In this setting, pessimistic and optimistic decision criteria have been formally justified. The computation by means of possibilistic logic inference of optimal decisions according to such criteria has been proposed. This paper presents an Answer Set Programm...
Article
We define a class of nested logic programs, called nested logic programs with ordered disjunction (LPODs + ), which makes it possible to specify conditional (qualitative) preferences by means of nested preference statements. To this end, we augment the syntax of Logic Programs with Ordered Disjunction (LPODs) to capture more general expressions. We...
Article
Full-text available
In this paper, we introduce a possibilistic argumentation-based decision making framework which is able to capture uncertain information and exceptions/defaults. In particular, we define the concept of a possibilistic decision making framework which is based on a possibilistic default theory, a set of decisions and a set of prioritized goals. This...
Conference Paper
Logic programs with ordered disjunction (or LPODs) have shown to be a flexible specification language able to model and reason about preferences in a natural way. However, in some realistic applications which use user preferences in the reasoning, information can be pervaded with vagueness and a preference-aware reasoning process that can handle un...
Chapter
Full-text available
In this paper we define a class of nested logic programs, nested logic programs with ordered disjunction (LP ODs +), which allows to specify qualitative preferences by means of nested preference expressions. For doing this we extend the syntax of logic programs with ordered disjunction (LPODs) to capture more general expressions. We define the LP O...
Conference Paper
Full-text available
There is a large body of research on software services, but the issues of communication and dynamic reconfiguration have received little attention, as have adaptation to environment and dynamic combination of service building blocks into new applications. Here, we present the approach of the FP7 alive project to the use of formal models of coordina...
Conference Paper
In this paper we define the semantics for capturing possibilistic ordered disjunction programs based on pstable semantics. The pstable semantics, based on paraconsistent logic, allows to treat inconsistency programs. Moreover being closer to possibilistic inference it allows to extend the necessity-values of the clauses to be considered, causing a...
Chapter
This paper presents an approach for specifying user prefer-ences related to services by means of a preference meta-model, which is mapped to logic programs with possibilistic ordered disjunction fol-lowing a Model-Driven Methodology (MDM). MDM allows to specify problem domains by means of meta-models which can be converted to in-stance models or ot...
Conference Paper
This paper presents a middleware to help designers in the implementation of contract-aware agent-based services. The middleware provides several components, including a contract manager, a communication manager and a workflow manager, which combine to allow agents to manage contracts and the actions associated with them. The middleware is built as...
Article
Full-text available
Reputation-based Governance (Rebag) is a framework to address governance problems that hinges on the reputation of the relevant actors. It functions thanks to an appropriate Web-based information system that encompasses the concept of Internet-based Reputation System, of which eBay represents an example. Rebag-Ware is a demonstrator of such an info...
Article
Full-text available
In this paper we describe our orchestration model for IRS-III. IRS-III is a framework and platform for developing WSMO based semantic web services. Orchestration specifies how a complex web service calls subordinate web services. Our orchestration model is state-based: control and data flow are defined by and in states respectively; web services an...

Network

Cited By