Attribution scores reflect how important the feature values in an input entity are for the output of a machine learning model. One of the most popular attribution scores is the SHAP score, which is an instantiation of the general Shapley value used in coalition game theory. The definition of this score relies on a probability distribution on the entity population. Since the exact distribution is generally unknown, it needs to be assigned subjectively or be estimated from data, which may lead to misleading feature scores. In this paper, we propose a principled framework for reasoning on SHAP scores under unknown entity population distributions. In our framework, we consider an uncertainty region that contains the potential distributions, and the SHAP score of a feature becomes a function defined over this region. We study the basic problems of finding maxima and minima of this function, which allows us to determine tight ranges for the SHAP scores of all features. In particular, we pinpoint the complexity of these problems, and other related ones, showing them to be intractable. Finally, we present experiments on a real-world dataset, showing that our framework may contribute to a more robust feature scoring.

In the deeply interconnected world we live in, pieces of information link domains all around us. As graph databases embrace effectively relationships among data and allow processing and querying these connections efficiently, they are rapidly becoming a popular platform for storage that supports a wide range of domains and applications. As in the relational case, it is expected that data preserves a set of integrity constraints that define the semantic structure of the world it represents. When a database does not satisfy its integrity constraints, a possible approach is to search for a ‘similar’ database that does satisfy the constraints, also known as a repair. In this work, we study the problem of computing subset and superset repairs for graph databases with data values using a notion of consistency based on having a set of Reg-GXPath expressions as integrity constraints. We show that for positive fragments of Reg-GXPath these problems admit a polynomial-time algorithm, while the full expressive power of the language renders them intractable.

This paper considers complex marine operations involving the coordinated motion of several ships. Each ship is controlled by an on-board computer, under captain supervision; so the ship is a quasi-robot ship. A computational procedure, able to embed a priori knowledge, was devised for planning of the ships motion control, to make them follow adequate trajectories. The main idea has been to mimic the typical maneuver when parking a car: turn the wheel to one side, and then to the other side; this may be seen as a partial bang-bang control strategy. In general, this type of maneuver do adapt to the control of non-holonomic vehicles, when a vehicle starts from a certain position and attitude and must arrive to another position and attitude. The paper introduces a genetic procedure for control planning using partial bang-bang control. A complete operation, the case of oil spill over confinement, is described, presenting results of the genetic optimization procedure.

This papers introduces a current research on avionic distributed control systems, using smart components. The research focus on fuel management systems. The nearest experimental target is real flight testing into three years. For safety reasons the new distributed system has to react with pertinent reconfigurations when there are problems in the system, as detected by the smart components. Likewise, it is possible that the fuel plant changes, for instance when extra tanks are added, so the distributed control system has to reconfigure its functionality. The specific experimental platform for the research is an helicopter. The paper describes the control problem, the control distribution concept, the smart components, and the present research for reconfiguration.