There is great potential in leveraging Artificial Intelligence (AI) systems to optimize complex infrastructures, automate difficult tasks, or support autonomy and coordination between networked devices. However, advances in state-of-the-art AI often neglect features and/or requirements that businesses care deeply about, namely traceability and explainability. While majority of research concerning Explainable AI remains focused on weight modelling and timid gray-box approaches, the state-of-the-art has not explored much the deployment of semi-physical architectures combining fuzzy rule-based systems with more opaque models to improve explainability. This contribution aims to explore and make the case for a middle ground of mixed AI architectures that combine the performance of black-box AI models with a more explainable overall architecture, enabling operators to use them, while still retaining the core aspects of explainability, when compared to full black-box AI systems. This work contextualizes a potential application of such approach to the problem of Service Level Agreement compliance, in a case of microservice allocation decision over cloud (and cloud-like) infrastructures.

The proliferation of digital artifacts with various computing capabilities, along with the emergence of edge computing, offers new possibilities for the development of Machine Learning solutions.These new possibilities have led to the popularity of Federated Learning (FL).While there are many existing works focusing on various aspects of the FL process, the issue of the effective problem diagnosis in FL systems remains largely unexplored.In this work, we have set out to artificially simulate the training process of four selected approaches to FL topology and compare their resulting performance.After noticing concerning disturbances throughout their training process, we have successfully identified their source as the problem of exploding gradients.We have then made modifications to the model structure and analyzed the new results.Finally, we have proposed continuous monitoring of the FL training process through the local computation of a selected metric.

Federated learning (FL) is a decentralized approach that aims at training a global model with the help of multiple devices, without collecting or revealing individual clients' data.The training of a federated model is conducted in communication rounds.Still, in certain scenarios, numerous communication rounds are impossible to perform.In such cases, a one-shot FL is utilized, where the number of communication rounds is limited to one.In this article, the idea of one-shot FL is enhanced with the usage of adversarial data, exploring and illustrating the possibilities to improve the performance of resulting global models, including scenarios with non-IID data, for image classification datasets: MNIST and CIFAR-10.

Reusing ontologies in practice is still very challenging, especially when multiple ontologies are (jointly) involved. Moreover, despite recent advances, the realization of systematic ontology quality assurance remains a difficult problem. In this work, the quality of thirty biomedical ontologies, and the Computer Science Ontology are investigated, from the perspective of a practical use case. Special scrutiny is given to cross-ontology references, which are vital for combining ontologies. Diverse methods to detect potential issues are proposed, including natural language processing and network analysis. Moreover, several suggestions for improving ontologies and their quality assurance processes are presented. It is argued that while the advancing automatic tools for ontology quality assurance are crucial for ontology improvement, they will not solve the problem entirely. It is ontology reuse that is the ultimate method for continuously verifying and improving ontology quality, as well as for guiding its future development. Specifically, multiple issues can be found and fixed primarily through practical and diverse ontology reuse scenarios.