Abstract
Many current AutoML platforms include a very large space of alternatives (the configuration space) that make it difficult to identify the best alternative for a given dataset. In this paper we explore a method that can reduce a large configuration space to a significantly smaller one and so help to reduce the search time for the potentially best workflow. We empirically validate the method on a set of workflows that include four ML algorithms (SVM, RF, LogR and LD) with different sets of hyperparameters. Our results show that it is possible to reduce the given space by more than one order of magnitude, from a few thousands to tens of workflows, while the risk that the best workflow is eliminated is nearly zero. The system after reduction is about one order of magnitude faster than the original one, but still maintains the same predictive accuracy and loss. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Deep learning approaches require a large amount of data to be transferred to centralized entities. However, this is often not a feasible option in healthcare, as it raises privacy concerns over sharing sensitive information. Federated Learning (FL) aims to address this issue by allowing machine learning without transferring the data to a centralized entity. FL has shown great potential to ensure privacy in digital healthcare while maintaining performance. Despite this, there is a lack of research on the impact of different types of data heterogeneity on the results. In this study, we research the robustness of various FL strategies on different data distributions and data quality for glaucoma diagnosis using retinal fundus images. We use RetinaQualEvaluator to generate quality labels for the datasets and then a data distributor to achieve our desired distributions. Finally, we evaluate the performance of the different strategies on local data and an independent test dataset. We observe that federated learning shows the potential to enable high-performance models without compromising sensitive data. Furthermore, we infer that FedProx is more suitable to scenarios where the distributions and quality of the data of the participating clients is diverse with less communication cost.

Abstract
In recent years, the increasing availability of distributed data has led to a growing interest in transfer learning across multiple nodes. However, local data may not be adequate to learn sufficiently accurate models, and the problem of learning from multiple distributed sources remains a challenge. To address this issue, Machine Learning Data Markets (MLDM) have been proposed as a potential solution. In MLDM, autonomous agents exchange relevant data in a cooperative relationship to improve their models. Previous research has shown that data exchange can lead to better models, but this has only been demonstrated with only two agents. In this paper, we present an extended evaluation of a simple version of the MLDM framework in a collaborative scenario. Our experiments show that data exchange has the potential to improve learning performance, even in a simple version of MLDM. The findings conclude that there exists a direct correlation between the number of agents and the gained performance, while an inverse correlation was observed between the performance and the data batch sizes. The results of this study provide important insights into the effectiveness of MLDM and how it can be used to improve learning performance in distributed systems. By increasing the number of agents, a more efficient system can be achieved, while larger data batch sizes can decrease the global performance of the system. These observations highlight the importance of considering both the number of agents and the data batch sizes when designing distributed learning systems using the MLDM framework.

Abstract

Abstract
The growing use of data-driven decision systems based on Artificial Intelligence (AI) by governments, companies and social organizations has given more attention to the challenges they pose to society. Over the last few years, news about discrimination appeared on social media, and privacy, among others, highlighted their vulnerabilities. Despite all the research around these issues, the definition of concepts inherent to the risks and/or vulnerabilities of data-driven decision systems is not consensual. Categorizing the dangers and vulnerabilities of data-driven decision systems will facilitate ethics by design, ethics in design and ethics for designers to contribute to responsibleAI. Themain goal of thiswork is to understand which types of AI risks/ vulnerabilities are Ethical and/or Technological and the differences between human vs machine classification. We analyze two types of problems: (i) the risks/ vulnerabilities classification task by humans; and (ii) the risks/vulnerabilities classification task by machines. To carry out the analysis, we applied a survey to perform human classification and the BERT algorithm in machine classification. The results show that even with different levels of detail, the classification of vulnerabilities is in agreement in most cases.

Abstract
The human brain works in such a complex way that we have not yet managed to decipher its functional mysteries [...]