Information systems face significant challenges in today’s constantly evolving digital environments, including dynamic data, heterogeneous sources, and analytical complexities, which directly impact decision-making processes and organizational competitiveness. Data alignment, the process of aligning different sources using their schema and instances, has become a vital solution for ensuring data consistency and enabling effective data exploration. However, existing methods often rely on static approaches which lack adaptability to dynamic data environments and require full recomputation with every change. This study provides an extended evaluation of our previously proposed incremental alignment approach, IDAGEmb, which leverages dynamic graph embedding techniques to refine alignments progressively. Unlike traditional static methods, IDAGEmb adapts to changes in real time, efficiently handling schema modifications and evolving data instances. Our evaluation highlights significant improvements in managing heterogeneous data, optimizing resource usage, and maintaining alignment accuracy in dynamic environments. By integrating incremental graph embeddings, this approach offers a solution for dynamic data environments, providing organizations with consistent and actionable insights. This work builds upon our earlier results, offering a new perspective on data alignment for evolving datasets and emphasizing the effectiveness of dynamic embedding techniques.

Federated Learning (FL) is a decentralized paradigm that enables a client-server architecture to collaboratively train a global Artificial Intelligence model without sharing raw data, thereby preserving privacy. A key challenge in FL is Non-IID data. Quantity Skew (QS) is a particular problem of Non-IID, where clients hold highly heterogeneous data volumes. Clustered Federated Learning (CFL) is an emergent variant of FL that presents a promising solution to Non-IID problem. It improves models' performance by grouping clients with similar data distributions into clusters. CFL methods generally fall into two operating strategies. In the first strategy, clients select the cluster that minimizes the local training loss. In the second strategy, the server groups clients based on local model similarities. However, most CFL methods lack systematic evaluation under QS but present significant challenges because of it.

Clustering is an important data mining task which is widely spread in various domains such as biology, finance, marketing, healthcare, and social sciences. It allows the end user to discover, through built clusters, relationships within data. Many non-expert users perceive clustering as an "easy" task because it always produces a result. However, choosing a clustering algorithm at random, without proper parameter tuning, often leads to poor results. In particular, an important choice when applying a clustering algorithm to a specific dataset is the similarity measure. Since clustering algorithms rely on similarities between data points to build clusters, the chosen similarity measure should fit the data as accurately as possible in order to form the best clusters. Mixed Data are data that are characterized by numerical as well as categorical attributes. When clustering mixed data, the same similarity measure cannot be used for the two attribute types. Commonly a pair of similarity measures is used, one dedicated to numerical attributes and one dedicated to categorical attributes. The choice of these two most appropriate similarity measures is very important in mixed data, as it significantly affects the clustering performance.

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.

In many domains, we face heterogeneous data with both numeric and categorical attributes. Clustering such data is challenging because the notion of similarity is not well defined due to the multiple data types. Existing clustering algorithms for these data are mainly based on two strategies: the homogenization one where all attributes are converted to a single type and the mixed one where similarity measures for the different data types are combined to define a similarity measure for heterogeneous data. We propose a framework in which we evaluate and compare several clustering algorithms using these two strategies on many real-world data sets. Then, motivated by the importance of similarity in clustering and the diversity of similarity measures for each data type, we proposed as a second study, to evaluate how their choice affects the performance of clustering algorithms using the mixed strategy. Our results suggest that the mixed strategy is preferable to the homogenization one since it uses adapted similarity measures for the different data types. Furthermore, the choice of similarity measures is very important for most of used mixed methods and an optimal choice may lead to great improvements compared to classically used similarity measures.

International audience

Using data warehouses to analyse multidimensional data is a significant task in company decision-making. The need for analyzing data stored in different data warehouses generates the requirement of merging them into one integrated data warehouse. The data warehouse merging process is composed of two steps: matching multidimensional components and then merging them. Current approaches do not take all the particularities of multidimensional data warehouses into account, e.g., only merging schemata, but not instances; or not exploiting hierarchies nor fact tables. Thus, in this paper, we propose an automatic merging approach for star schema-modeled data warehouses that works at both the schema and instance levels. We also provide algorithms for merging hierarchies, dimensions and facts. Eventually, we implement our merging algorithms and validate them with the use of both synthetic and benchmark datasets.

Performance anomalies are a core problem in modern information systems, that affects the execution of the hosted applications. The detection of these anomalies often relies on the analysis of the application execution logs. The current most effective approach is to detect samples that differ from a learnt nominal model. However, current methods often focus on detecting sequential anomalies in logs, neglecting the time elapsed between logs, which is a core component of the performance anomaly detection. In this paper, we develop a new model for performance anomaly detection that captures temporal deviations from the nominal model, by means of a sliding window data representation. This nominal model is trained by a Long Short-Term Memory neural network, which is appropriate to represent complex sequential dependencies. We assess the effectiveness of our model on both simulated and real datasets. We show that it is more robust to temporal variations than current state-of-the-art approaches, while remaining as effective.

Clustering is a data analysis method for extracting knowledge by discovering groups of data called clusters. Among these methods, state-of-the-art density-based clustering methods have proven to be effective for arbitrary-shaped clusters. Despite their encouraging results, they suffer to find low-density clusters, near clusters with similar densities, and high-dimensional data. Our proposals are a new characterization of clusters and a new clustering algorithm based on spatial density and probabilistic approach. First of all, sub-clusters are built using spatial density represented as probability density function (p.d.f) of pairwise distances between points. A method is then proposed to agglomerate similar sub-clusters by using both their density (p.d.f) and their spatial distance. The key idea we propose is to use the Wasserstein metric, a powerful tool to measure the distance between p.d.f of sub-clusters. We show that our approach outperforms other state-of-the-art density-based clustering methods on a wide variety of datasets.

International audience

The identification of alignments between heterogeneous ontologies is one of the main research issues in the semantic web.The manual matching of the ontologies is a complex, time consuming and an error prone task.Therefore, ontology matching systems aims to automate this process.Usually, these systems perform the matching process by combining element and structural level matchers.Selecting the optimal string similarity measure associated with its threshold is an important issue in order to enhance the effectiveness of the element level matcher, which in turn will improve the whole ontology system results.In this paper, we present POMap, an ontology matching system based on a syntactic study covering element and structural levels.For the element level matcher we have adopted the best configuration based on the analysis of the performances of many string similarity measures associated with their thresholds.For the structural level, we have performed a syntactic study on both subclasses and siblings in order to infer the structural similarity.Our proposed matching system is validated and evaluated on the Anatomy, the Conference and the Large Biomedical tracks provided by the benchmark of OAEI 2016 ontology matching campaign.

Collaboratively edited articles such as in Wikipedia suffer from well-identified problems regarding their quality, e.g., information accuracy, reputability of third-party sources, vandalism. Due to the huge number of articles and the intensive edit rate, the manual evaluation of article content quality is inconceivable. In this paper, we tackle the problem of automatically establishing the quality of Wikipedia articles. Evidences are shown to consider the interactions between authors and articles to assess the quality score. Collaborations between authors and reviewers are also considered to reinforce the discriminative process. This work gives a generic formulation of the Mutual Reinforcement principle held between articles quality and authors authority and take explicitly advantage of the co-edits graph generated by individuals. Experiments conducted on a set of representative data from Wikipedia show the effectiveness of our approach.

This paper focuses on data warehouse modelling. The conceptual model we defined, is based on object concepts extended with specific concepts like generic classes, temporal classes and archive classes. The temporal classes are used to store the detailed evolutions and the archive classes store the summarised data evolutions. We also provide a flexible concept allowing the administrator to define historised parts and non-historised parts into the warehouse schema. Moreover, we introduce constraints which configure the data warehouse behaviour and these various parts. To validate our propositions, we describe a prototype dedicated to the data warehouse design.