Ing. Jakub Peleška

Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning (RDL) has emerged as a novel paradigm wherein RDBs are conceptualized as graph structures, enabling the application of various graph neural architectures to effectively address these tasks. However, given its novelty, there is a lack of analysis into the relationships between the performance of various RDL models and the characteristics of the underlying RDBs. In this study, we present REDELEX−a comprehensive exploration framework for evaluating RDL models of varying complexity on the most diverse collection of over 70 RDBs, which we make available to the community. Benchmarked alongside key representatives of classic methods, we confirm the generally superior performance of RDL while providing insights into the main factors shaping performance, including model complexity, database sizes and their structural properties.

Transformer models have continuously expanded into all machine learning domains convertible to the underlying sequence-to-sequence representation, including tabular data. However, while ubiquitous, this representation restricts their extension to the more general case of relational databases. In this paper, we introduce a modular neural message-passing scheme that closely adheres to the formal relational model, enabling direct end-to-end learning of tabular transformers from database storage systems. We address the associated challenges of appropriate learning data representation and loading, which are critical in the database setting, and compare our approach against a number of representative models from various related fields across a significantly wide range of datasets. Our results then demonstrate superior performance of this newly proposed class of neural architectures.

Explainable AI (XAI) is an actively growing field. When choosing a suitable XAI method, one can get overwhelmed by the number of existing approaches, their properties, and taxonomies. In this paper, we approach the problem of navigating the XAI landscape from a practical perspective of emerging regulatory needs. Particularly, the recently approved AI Act gives users of AI applications classified as “high-risk” the right to explanation. We propose a practical framework to navigate between these high-risk domains and the diverse perspectives of different explainees’ roles via six core XAI desiderata. The introduced desiderata can then be used by stakeholders with different backgrounds to make informed decisions about which explainability technique is more appropriate for their use case. By supporting context-sensitive assessment of explanation techniques, our framework contributes to the development of more trustworthy AI systems.