Chiara Manganini

In the context of deterministic scientific simulations, formal validity requirements have typically been defined to help us reason about the relationship between the mathematical model underlying the target system and the computational model used to simulate it. With machine learning simulations entering the picture, we argue that these formal requirements need to be reviewed, as the objects to which they apply have significantly changed. This is due to several reasons: the target system is no longer an available system object of investigation; the probabilistic mathematical model is abstracted from the target system through the mediation of the computational model, which however remains largely opaque to us due to its high complexity. For these reasons, we formulate weaker, probabilistic versions of the traditional relations of Simulation, Bisimulation, and Approximate Simulation. Accordingly, we define three corresponding validity criteria that capture a range of cases, from the strongest to the weakest, depending on the extent to which the machine learning model can be assumed to correctly represent its target system.

In the present work, we develop a novel information-theoretic and logic-based approach to data bias in Machine Learning predictions and show its relevance in the specific context of fairness evaluation. We frame predictions made on biased data as Ulam games, which formalise key aspects of data-driven inference, and from which a variation of the rational non-monotonic consequence relation can be defined. We investigate this framework to model how differential levels of noise in input features impact Machine Learning predictions. To the best of our knowledge, this is the first game-theoretic formalisation of ML unfairness.

By analogy with Kripke’s claim that no fact of the matter can determine the meaning of a word, the sceptical paradox of implementation is an argument to the conclusion that no fact of the matter can determine the function of a computational artefact. The paradox targets the prevailing view within the philosophy of computer science, according to which the function of a computational artefact is to be identified with the content of its functional specification, a mathematical object that formalises the intentions of the artefact’s designer. In existing formulations, such a view requires the existence of certain semantic intentions in the head of the designer. However, if we accept Kripke’s claim that there is no such thing as a mental state of semantic intention, this leaves ultimately indeterminate what is the function implemented by a computational artefact. Just as Kripke’s solution to the paradox requires replacing the received conception of language with a very different one, so the sceptical paradox for computational artefacts forces us to explore a new perspective on computational artefacts that, this time, does without semantic intentions.

The second edition of the BEWARE workshop, co-located with the AIxIA 2023 conference, was held in Rome on November 6, 2023. The workshop focused on the emerging ethical aspects of AI, particularly addressing Bias, Risk, Explainability, and the role of Logic and Logic Programming. The event brought together a diverse group of researchers and practitioners to discuss and explore solutions for ethical decision-making in AI. This year, the workshop saw significant participation, with 9 accepted high-quality submis- sions, 5 as long papers and 4 as short papers (out of a total of 11 submitted papers), rigorously peer-reviewed by our Program Committee.

The widespread emergence of phenomena of bias is certainly among the most adverse impacts of new data-intensive sciences and technologies. The causes of such undesirable behaviours must be traced back to data themselves, as well as to certain design choices of machine learningMachine learning (ML) algorithms. The task of modelling bias from a logical point of view requires to extend the vast family of defeasible logicsDefeasible logic and logics for uncertain reasoningReasoninguncertain with ones that capture some few, fundamental properties of biased predictions. However, a logically grounded approach to machine learningMachine learning (ML) fairness is still at early stages in the literature. In this paper, we discuss current approaches to the topic, formulate general logical desiderata for logics to reason with and about bias, and provide a novel approach.