Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key XAI notions—remarkably including the term “explanation”, which still lacks a precise definition. To bridge this gap, this paper introduces a unifying mathematical framework allowing the rigorous definition of key XAI notions and processes, using the well-funded formalism of Category theory. In particular, we show that the introduced framework allows us to: (i) model existing learning schemes and architectures in both XAI and AI in general, (ii) formally define the term “explanation”, (iii) establish a theoretical basis for XAI taxonomies, and (iv) analyze commonly overlooked aspects of explaining methods. As a consequence, the proposed categorical framework represents a significant step towards a sound theoretical foundation of explainable AI by providing an unambiguous language to describe and model concepts, algorithms, and systems, thus also promoting research in XAI and collaboration between researchers from diverse fields, such as computer science, cognitive science, and abstract mathematics.

Categorical Foundation of Explainable AI: A Unifying Theory / Giannini, Francesco; Fioravanti, Stefano; Barbiero, Pietro; Tonda, Alberto; Lio, Pietro; Di Lavore, Elena. - 2155 CCIS:(2024), pp. 185-206. (Intervento presentato al convegno 2nd World Conference on Explainable Artificial Intelligence, xAI 2024 tenutosi a Valletta; mlt) [10.1007/978-3-031-63800-8_10].

Categorical Foundation of Explainable AI: A Unifying Theory

Lio, Pietro;
2024

Abstract

Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key XAI notions—remarkably including the term “explanation”, which still lacks a precise definition. To bridge this gap, this paper introduces a unifying mathematical framework allowing the rigorous definition of key XAI notions and processes, using the well-funded formalism of Category theory. In particular, we show that the introduced framework allows us to: (i) model existing learning schemes and architectures in both XAI and AI in general, (ii) formally define the term “explanation”, (iii) establish a theoretical basis for XAI taxonomies, and (iv) analyze commonly overlooked aspects of explaining methods. As a consequence, the proposed categorical framework represents a significant step towards a sound theoretical foundation of explainable AI by providing an unambiguous language to describe and model concepts, algorithms, and systems, thus also promoting research in XAI and collaboration between researchers from diverse fields, such as computer science, cognitive science, and abstract mathematics.
2024
2nd World Conference on Explainable Artificial Intelligence, xAI 2024
Category Theory; Explainable AI; XAI Foundations and Taxonomies
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Categorical Foundation of Explainable AI: A Unifying Theory / Giannini, Francesco; Fioravanti, Stefano; Barbiero, Pietro; Tonda, Alberto; Lio, Pietro; Di Lavore, Elena. - 2155 CCIS:(2024), pp. 185-206. (Intervento presentato al convegno 2nd World Conference on Explainable Artificial Intelligence, xAI 2024 tenutosi a Valletta; mlt) [10.1007/978-3-031-63800-8_10].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1728699
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact