Search

Dung's Argumentation Framework (AF) has been extended in several directions, including the possibility of representing uncertainty about the existence of arguments and attacks. In this regard, two main proposals have been introduced in the literature: Probabilistic Argumentation Framework (PrAF) and Incomplete Argumentation Framework (iAF). PrAF is an extension of AF with probability theory, thus representing quantified uncertainty. In contrast, iAF represents unquantified uncertainty, that is it can be seen as a special case where we only know that some elements (arguments or attacks) are uncertain. In this paper, we first address the problem of computing the probability that a given argument is accepted in PrAF. This is carried out by introducing the concept of probabilistic explanation for any given (probabilistic) extension. We show that the complexity of the problem is FP # P -hard and propose polynomial approximation algorithms with bounded additive error for PrAFs where odd-length cycles are forbidden. We investigate the approximate complexity of the related FP # P -hard problems of credulous and skeptical acceptance in PrAF, showing that they are generally harder than the problem of computing the probability that a given argument is accepted. Next we consider iAF and, after showing some equivalence properties among classes of iAFs, we study iAF as a special case of PrAF where uncertain elements have associated a probability equal to 1/2. Finally, given this result, we investigate the relationships between iAF acceptance problems and probabilistic acceptance in PrAF. [ABSTRACT FROM AUTHOR]

This paper provides an extensive overview of the use of knowledge graphs in the context of Explainable Machine Learning. As of late, explainable AI has become a very active field of research by addressing the limitations of the latest machine learning solutions that often provide highly accurate, but hardly scrutable and interpretable decisions. An increasing interest has also been shown in the integration of Knowledge Representation techniques in Machine Learning applications, mostly motivated by the complementary strengths and weaknesses that could lead to a new generation of hybrid intelligent systems. Following this idea, we hypothesise that knowledge graphs, which naturally provide domain background knowledge in a machine-readable format, could be integrated in Explainable Machine Learning approaches to help them provide more meaningful, insightful and trustworthy explanations. Using a systematic literature review methodology we designed an analytical framework to explore the current landscape of Explainable Machine Learning. We focus particularly on the integration with structured knowledge at large scale, and use our framework to analyse a variety of Machine Learning domains, identifying the main characteristics of such knowledge-based, explainable systems from different perspectives. We then summarise the strengths of such hybrid systems, such as improved understandability, reactivity, and accuracy, as well as their limitations, e.g. in handling noise or extracting knowledge efficiently. We conclude by discussing a list of open challenges left for future research. [ABSTRACT FROM AUTHOR]

Most of the algorithms developed within the Constraint Satisfaction Problem (CSP) framework cannot be used as such to solve interactive decision support problems, like product configuration. Indeed, in such problems, the user is in charge of assigning values to variables. Global consistency maintaining is only one among several functionalities that should be offered by a CSP-based platform in order to help the user in her task; other important functionalities include providing explanations for some user''s choices and ways to restore consistency.This paper presents an extension of the CSP framework in this direction. The key idea consists in considering and handling the user''s choices as assumptions.  From a theoretical point of view, the complexity issues of various computational tasks involved in interactive decision support problems are investigated. The results cohere with what is known when Boolean constraints are considered and show all the tasks intractable in the worst case. Since interactivity requires short response times, intractability must be circumvented some way. To this end, we present a new method for compiling configuration problems, that can be generalized to valued CSPs. Specifically, an automaton representing the set of solutions of the CSP is first computed off-line, then this data structure is exploited so as to ensure both consistency maintenance and computation of maximal consistent subsets of user''s choices in an efficient way. [Copyright &y& Elsevier]

Research in the social sciences has shown that expectations are an important factor in explanations as used between humans: rather than explaining the cause of an event per se, the explainer will often address another event that did not occur but that the explainee might have expected. For AI-powered systems, this finding suggests that explanation-generating systems may need to identify such end user expectations. In general, this is a challenging task, not the least because users often keep them implicit; there is thus a need to investigate the importance of such an ability. In this paper, we report an empirical study with 181 participants who were shown outputs from a text classifier system along with an explanation of why the system chose a particular class for each text. Explanations were both factual , explaining why the system produced a certain output or counterfactual , explaining why the system produced one output instead of another. Our main hypothesis was explanations should align with end user expectations; that is, a factual explanation should be given when the system's output is in line with end user expectations, and a counterfactual explanation when it is not. We find that factual explanations are indeed appropriate when expectations and output match. When they do not, neither factual nor counterfactual explanations appear appropriate, although we do find indications that our counterfactual explanations contained at least some necessary elements. Overall, this suggests that it is important for systems that create explanations of AI systems to infer what outputs the end user expected so that factual explanations can be generated at the appropriate moments. At the same time, this information is, by itself, not sufficient to also create appropriate explanations when the output and user expectations do not match. This is somewhat surprising given investigations of explanations in the social sciences, and will need more scrutiny in future studies. [ABSTRACT FROM AUTHOR]

Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these " stakeholders' desiderata ") in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often remains unclear how explainability approaches are supposed to achieve the goal of satisfying stakeholders' desiderata. This paper discusses the main classes of stakeholders calling for explainability of artificial systems and reviews their desiderata. We provide a model that explicitly spells out the main concepts and relations necessary to consider and investigate when evaluating, adjusting, choosing, and developing explainability approaches that aim to satisfy stakeholders' desiderata. This model can serve researchers from the variety of different disciplines involved in XAI as a common ground. It emphasizes where there is interdisciplinary potential in the evaluation and the development of explainability approaches. [ABSTRACT FROM AUTHOR]