2

Recommender systems are vital to online platforms, with Graph Neural Network (GNN) approaches showing excellent accuracy. However, beyond-accuracy metrics like diversity, serendipity, and fairness significantly impact user satisfaction. This review examines these dimensions in GNN-based recommenders, analyzing recent developments that balance accuracy with these broader objectives. We explore how various model development stages—from data preprocessing to training methodologies—affect these metrics. The paper addresses practical challenges in maintaining high accuracy while enhancing diversity, serendipity, and fairness, and outlines future research directions for more holistic GNN-based recommender systems. Our contribution lies in providing a comprehensive understanding of the multidimensional considerations essential to effective recommender system design.

This study investigates how community structure and homophily influence Graph Neural Networks (GNNs) in semi-supervised node classification tasks. By systematically modifying eight datasets and measuring GNN performance with and without these structural properties, we demonstrate their significant impact on classification accuracy and reveal insights about their interaction. We introduce an information-theoretic metric to quantify community-label correlation, providing practical guidelines for model selection based on graph structure. Our findings enhance understanding of GNN capabilities and improve model selection for semi-supervised node classification tasks.

This study introduces natural language explanations designed to promote more thoughtful reasoning about online videos and increase awareness of potentially biased or misleading content. We developed an end-to-end pipeline that extracts reflection triggers about video sources, topics, emotions, and sentiment to help users actively evaluate video usefulness. Our between-subjects study examining controversial topics reveals that users’ alignment with video messages significantly impacts perceived usefulness. While explanations were rated highly, they didn’t alter overall usefulness perceptions compared to videos alone. Notably, users with extreme negative alignment found videos less useful regardless of explanations and were more confident in their assessments. We interpret these findings through cognitive dissonance theory and propose design implications for explanations aimed at raising awareness about online deception.

This study examines three unsupervised dimensionality reduction techniques (PCA, UMAP, and VAEs) for toxicology classification tasks. The research compares these embedding methods against standard molecular fingerprint models and explores transfer learning by training embedders on external chemical compound datasets. By testing various embedding dimensions and external dataset sizes, the findings demonstrate that UMAP can effectively complement established techniques like PCA and VAE for pre-compression in toxicology. However, VAE’s generative approach shows superior performance in pre-compression for classification accuracy.

A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.