Recommending a point-of-interest (POI) a user will visit next based on temporal and spatial context information is an important task in mobile-based applications. Recently, several POI recommendation models based on conventional sequential-data modeling approaches have been proposed. However, such models focus on only a user's check-in sequence information and the physical distance between POIs. Furthermore, they do not utilize the characteristics of POIs or the relationships between POIs. To address this problem, we propose CAPE, the first content-aware POI embedding model which utilizes text content that provides information about the characteristics of a POI. CAPE consists of a check-in context layer and a text content layer. The check-in context layer captures the geographical influence of POIs from the check-in sequence of a user, while the text content layer captures the characteristics of POIs from the text content. To validate the efficacy of CAPE, we constructed a large-scale POI dataset. In the experimental evaluation, we show that the performance of the existing POI recommendation models can be significantly improved by simply applying CAPE to the models.

Addressing imbalanced or long-tailed data is a major challenge in visual recognition tasks due to disparities between training and testing distributions and issues with data noise. We propose the Wrapped Cauchy Distributed Angular Softmax (WCDAS), a novel softmax function that incorporates data-wise Gaussianbased kernels into the angular correlation between feature representations and classifier weights, effectively mitigating noise and sparse sampling concerns. The class-wise distribution of angular representation becomes a sum of these kernels. Our theoretical analysis reveals that the wrapped Cauchy distribution excels the Gaussian distribution in approximating mixed distributions.Additionally, WCDAS uses trainable concentration parameters to dynamically adjust the compactness and margin of each class. Empirical results confirm label-aware behavior in these parameters and demonstrate WCDAS's superiority over other state-of-the-art softmaxbased methods in handling long-tailed visual recognition across multiple benchmark datasets. The code is public available.

Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound–kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.

Treating patients with major depressive disorder is challenging because it takes several months for antidepressants prescribed for the patients to take effect. This limitation may result in increased risks and treatment costs. To address this limitation, an accurate antidepressant response prediction model is needed. Recently, several studies have proposed models that extract useful features such as neuroimaging biomarkers and genetic variants from patient data, and use them as predictors for predicting the antidepressant responses of patients. However, it is impossible to utilize all the different types of predictors when making a clinical decision on what drugs to prescribe for a patient. Although a machine learning-based antidepressant response prediction model has been proposed to overcome this problem, the model cannot find the most effective antidepressant for a patient. Based on a neural network, we propose an Antidepressant Response Prediction Network (ARPNet) model capturing high-dimensional patterns from useful features. Based on a literature survey and data-driven feature selection, we extract useful features from patient data, and use the features as predictors. In ARPNet, the patient representation layer captures patient features and the antidepressant prescription representation layer captures antidepressant features. Utilizing the patient and antidepressant prescription representation vectors, ARPNet predicts the degree of antidepressant response. The experimental evaluation results demonstrate that our proposed ARPNet model outperforms machine learning-based models in predicting antidepressant response. Moreover, we demonstrate the applicability of ARPNet in downstream applications in use case scenarios.

Several geographical latent representation models that capture geographical influences among points-of-interest (POIs) have been proposed. Although the models improve POI recommendation performance, they depend on shallow methods that cannot effectively capture highly non-linear geographical influences from complex user-POI networks. In this paper, we propose a new graph-based geographical latent representation model (GGLR) which can capture highly non-linear geographical influences from complex user-POI networks. Our proposed GGLR considers two types of geographical influences: ingoing influences and outgoing influences. Based on a graph auto-encoder, geographical latent representations of ingoing and outgoing influences are trained to increase geographical influences between two consecutive POIs that frequently appear in check-in histories. Furthermore, we propose a graph neural network-based POI recommendation model (GPR) that uses the trained geographical latent representations of ingoing and outgoing influences for the estimation of user preferences. In the experimental evaluation on real-world datasets, we show that GGLR effectively captures highly non-linear geographical influences and GPR achieves state-of-the-art performance. CCS CONCEPTS • Information systems → Collaborative filtering.