Recent years have witnessed the remarkable success of recommendation systems (RSs) in alleviating the information overload problem. As a new paradigm of RSs, session-based recommendation (SR) specializes in users’ short-term preferences and aims at providing a more dynamic and timely recommendation based on ongoing interactions. This survey presents a comprehensive overview of the recent works on SR. First, we clarify the key definitions within SR and compare the characteristics of SR against other recommendation tasks. Then, we summarize the existing methods in two categories: sequential neural network based methods and graph neural network (GNN) based methods. The relevant frameworks and technical details are further introduced. Finally, we discuss the challenges of SR and new research directions in this area.
The session-based recommendation aims to predict users' immediate next actions based on their short-term behaviors reflected by past and ongoing sessions. Graph neural networks (GNNs) recently dominated the related studies, yet their performance heavily relies on graph structures, which are often predefined, task-specific, and designed heuristically. Furthermore, existing graph-based methods either neglect implicit correlations among items or consider explicit and implicit relationships altogether in the same graphs. We propose to decouple explicit and implicit relationships among items. As such, we can capture the prior knowledge encapsulated in explicit dependencies and learned implicit correlations among items simultaneously in a flexible and more interpretable manner for effective recommendations. We design a dual graph neural network that leverages the feature representations extracted by two GNNs: a graph neural network with a single gate (SG-GNN) and an adaptive graph neural network (A-GNN). The former models explicit dependencies among items. The latter employs a self-learning strategy to capture implicit correlations among items. Our experiments on four real-world datasets show our model outperforms state-of-the-art methods by a large margin, achieving 18.46% and 70.72% improvement in [email protected], and 49.10% and 115.29% improvement in [email protected] on Diginetica and LastFM datasets.
Personality differences are an important part of animal behavior research and a potential factor affecting the physiochemical response of animals to stimuli. Therefore, accurate classification of personality has an impact on animal experiment research that cannot be ignored. However, no completely objective methods have been noticed hitherto to be employed in aquatic animal personality studies. To address this issue, we established a personality analysis method based on machine learning (PAML) to avoid the influence of subjective factors. Then we analyzed the personality changes of swimming crab Portunus trituberculatus exposed to external stimuli i.e., food deprivation. Results showed that the high-accuracy PAML method could provide a comprehensive understanding of crab personality classification. Based on PAML, the personality of P. trituberculatus was detected to change dynamically under stress. After analyzing three typical personality characteristics: boldness, activity, and hesitancy, we found that the stability of boldness was the strongest, which is the best single candidate for personality evaluation, while the activity changed greatly under stress. This study confirms that animal personality changes dynamically with external factors. Based on PAML, we can not only avoid subjective factors and improve classification accuracy, but also quantitatively trace the dynamic influence of external factors on aquatic animal personality.