← Search

Gianvincenzo Alfano

14 accepted papers

2026

Semifactual Explanations for GNN-based Classification: Formal Foundations, Complexity and Computation

IJCAI 2026

Graph Neural Networks (GNNs) have become increasingly central to several analysis tasks in various domains, ranging, e.g., from social networks to molecular analysis. Understanding the decision-making process of GNNs is a critical challenge in machine learning, particularly when post-hoc explanation

Cited by 0Scholar
2025

Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation

IJCAI 2025

Counterfactual explanations (CXs) are widely recognised as an essential technique for providing recourse recommendations for AI models. However, it is not obvious how to determine CXs in model multiplicity scenarios, where equally performing but different models can be obtained for the same task. In

Cited by 0SourcePDFScholar
2025

Credulous Acceptance in High-Order Argumentation Frameworks with Necessities: An Incremental Approach (Abstract Reprint)

IJCAI 2025

Argumentation is an important research area in the field of AI. There is a substantial amount of work on different aspects of Dung's abstract Argumentation Framework (AF). Two relevant aspects considered separately so far are: i) extending the framework to account for recursive attacks and supports,

Cited by 0SourcePDFScholar
2025

Even-if Explanations: Formal Foundations, Priorities and Complexity

AAAI 2025technical

Explainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability queries attempt to answer why individual inputs are classified i…

Cited by 2SourcePDFScholar
2025

Featured Argumentation Framework: Semantics and Complexity

IJCAI 2025

Dung's Argumentation Framework (AF) has been extended in several directions to make knowledge representation and reasoning tasks more intuitive and/or expressive. We present a novel extension of AF called Featured AF (FAF), where each argument has associated a set of features expressed by means of u

Cited by 0SourcePDFScholar
2024

Complexity of Credulous and Skeptical Acceptance in Epistemic Argumentation Framework

AAAI 2024technical

Dung’s Argumentation Framework (AF) has been extended in several directions. Among the numerous proposed extensions, three of them seem to be of particular interest and have correlations between them. These extensions are: constrained AF (CAF), where AF is augmented with (strong) constraints; episte…

Cited by 5SourcePDFScholar
2024

General Epistemic Abstract Argumentation Framework: Semantics and Complexity

IJCAI 2024poster

Epistemic Abstract Argumentation Framework (EAAF) extends Dung's framework (AAF)---a central formalism in AI for modeling disputes among agents---by allowing the representation of epistemic knowledge. In particular, EAAF augments AAF with weak and strong epistemic attacks whose intuitive meaning is…

Cited by 0SourcePDFScholar
2023

Abstract Argumentation Framework with Conditional Preferences

AAAI 2023technical

Dung's abstract Argumentation Framework (AF) has emerged as a central formalism in the area of knowledge representation and reasoning. Preferences in AF allow to represent the comparative strength of arguments in a simple yet expressive way. Preference-based AF (PAF) has been proposed to extend AF…

Cited by 19SourcePDFScholar
2023

Preferences and Constraints in Abstract Argumentation

IJCAI 2023poster

In recent years there has been an increasing interest in extending Dung's framework to facilitate the knowledge representation and reasoning process. In this paper, we present an extension of Abstract Argumentation Framework (AF) that allows for the representation of preferences over arguments' tru…

Cited by 12SourcePDFScholar
2022

Incomplete Argumentation Frameworks: Properties and Complexity

AAAI 2022technical

Dung’s Argumentation Framework (AF) has been extended in several directions, including the possibility of representing unquantified uncertainty about the existence of arguments and attacks. The framework resulting from such an extension is called incomplete AF (iAF). In this paper, we first introduc…

Cited by 32SourcePDFScholar
2022

On Preferences and Priority Rules in Abstract Argumentation

IJCAI 2022poster

Dung's abstract Argumentation Framework (AF) has emerged as a central formalism for argumentation in AI. Preferences in AF allow to represent the comparative strength of arguments in a simple yet expressive way. In this paper we first investigate the complexity of the verification as well as cred…

Cited by 26SourcePDFScholar
2021

Argumentation Frameworks with Strong and Weak Constraints: Semantics and Complexity

AAAI 2021technical

Dung's abstract Argumentation Framework (AF) has emerged as a central formalism in formal argumentation. Key aspects of the success and popularity of Dung's framework include its simplicity and expressiveness. Integrity constraints help to express domain knowledge in a compact and natural way, thus…

Cited by 28SourcePDFScholar
2021

Defining the Semantics of Abstract Argumentation Frameworks through Logic Programs and Partial Stable Models (Extended Abstract)

IJCAI 2021poster

Extensions of Dung’s Argumentation Framework (AF) include the class of Recursive Bipolar AFs (Rec-BAFs), i.e. AFs with recursive attacks and supports. We show that a Rec-BAF \Delta can be translated into a logic program P_\Delta so that the extensions of \Delta under different semantics coincide wit…

Cited by 4SourcePDFScholar