Hypergraphs have attracted increasing attention in recent years thanks to their flexibility in naturally modeling a broad range of systems where high-order relationships exist among their interacting parts. This survey reviews the newly born hypergraph representation learning problem, whose goal is to learn a function to project objects—most commonly nodes—of an input hyper-network into a latent space such that both the structural and relational properties of the network can be encoded and preserved. We provide a thorough overview of existing literature and offer a new taxonomy of hypergraph embedding methods by identifying three main families of techniques, i.e., spectral, proximity-preserving, and (deep) neural networks. For each family, we describe its characteristics and our insights in a single yet flexible framework and then discuss the peculiarities of individual methods, as well as their pros and cons. We then review the main tasks, datasets, and settings in which hypergraph embeddings are typically used. We finally identify and discuss open challenges that would inspire further research in this field.

Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situations. However, making such accurate forecasts is not easy: many factors may influence the required time to complete a process instance. In this paper, we propose an approach based on deep Recurrent Neural Networks (specifically LSTMs) that is able to exploit arbitrary information associated to single events, in order to produce an as-accurate-as-possible prediction of the completion time of running instances. Experiments on real-world datasets confirm the quality of our proposal.

Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide. Broadly, the present survey overviews HNN architectures, training strategies, and applications. First, we break existing HNNs down into four design components: (i) input features, (ii) input structures, (iii) message-passing schemes, and (iv) training strategies. Second, we examine how HNNs address and learn HOIs with each of their components. Third, we overview the recent applications of HNNs in recommendation, bioinformatics and medical science, time series analysis, and computer vision. Lastly, we conclude with a discussion on limitations and future directions.

The latest developments in the field of artificial intelligence (AI) have given rise to many ethical and socio-economic concerns. Nonetheless, the impact of AI technologies is evident and tangible in our everyday life. This dichotomy leads to mixed feelings toward AI: people recognize the positive impact of AI, but they also show concerns, especially about their privacy and security. In this article, we try to understand whether the implicit and explicit attitudes toward AI are coherent. We investigated explicit and implicit attitudes toward AI by combining a self-report measure and an implicit measure, i.e., the implicit association test. We analyzed the explicit and implicit responses of 829 participants. Results revealed that while most of the participants explicitly express a positive attitude toward AI, their implicit responses seem to point in the opposite direction. Results also show that, in both the explicit and implicit measures, females show a more negative attitude than males, and people who work in the field of AI are inclined to be positive toward AI.

Accurate prediction of the completion time of a business process instance would constitute a valuable tool when managing processes under service level agreement constraints. Such prediction, however, is a very challenging task. A wide variety of factors could influence the trend of a process instance, and hence just using time statistics of historical cases cannot be sufficient to get accurate predictions. Here we propose a new approach where, in order to improve the prediction quality, both the control and the data flow perspectives are jointly used. To achieve this goal, our approach builds a process model which is augmented by time and data information in order to enable remaining time prediction. The remaining time prediction of a running case is calculated combining two factors: (a) the likelihood of all the following activities, given the data collected so far; and (b) the remaining time estimation given by a regression model built upon the data.