International audience

A large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed in recent years. Recently, thanks to new XAI evaluation metrics, it has become possible to compare these XAI solutions. However, selecting the most relevant XAI solution among all this diversity is still a tedious task, especially if a user has specific needs and constraints. In this paper, we propose AutoXAI, a framework that recommends the best XAI solution and its hyperparameters according to specified XAI evaluation metrics while considering the user's context (dataset, machine learning model, XAI needs and constraints). It adapts approaches from context-aware recommender systems on one side and strategies of optimization and evaluation from AutoML (Automated Machine Learning) on the other. Through two use cases, we show that AutoXAI recommends XAI solutions adapted to the user's needs with the best hyperparameters matching the user's constraints.

Data lakes are supposed to enable analysts to perform more efficient and efficacious data analysis by crossing multiple existing data sources, processes and analyses. However, it is impossible to achieve that when a data lake does not have a metadata governance system that progressively capitalizes on all the performed analysis experiments. The objective of this paper is to have an easily accessible, reusable data lake that capitalizes on all user experiences. To meet this need, we propose an analysis-oriented metadata model for data lakes. This model includes the descriptive information of datasets and their attributes, as well as all metadata related to the machine learning analyzes performed on these datasets. To illustrate our metadata solution, we implemented an application of data lake metadata management. This application allows users to find and use existing data, processes and analyses by searching relevant metadata stored in a NoSQL data store within the data lake. To demonstrate how to easily discover metadata with the application, we present two use cases, with real data, including datasets similarity detection and machine learning guidance.

OLAP is the main paradigm for flexible and effective exploration of multidimensional cubes in data warehouses. During an OLAP session the user analyzes the results of a query and determines a new query that will give her a better understanding of information. Given the huge size of the data space, this exploration process is often tedious and may leave the user disoriented and frustrated. This paper presents an OLAP tool named Falseto (Former AnalyticaL Sessions for lEss Tedious Olap), that is meant to assist query and session composition, by letting the user summarize, browse, query, and reuse former analytical sessions. Falseto's implementation on top of a formal framework is detailed. We also report the experiments we run to obtain and analyze real OLAP sessions and assess Falseto with them. Finally, we discuss how Falseto can be seen as a starting point for bridging OLAP with exploratory search, a search paradigm centered on the user and the evolution of her knowledge.