Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation

Group recommendation aims to recommend items to a group of users. In this work, we study group recommendation in a particular scenario, namely occasional group recommendation, where groups are formed ad hoc and users may just constitute a group for the first time—that is, the historical group-item interaction records are highly limited. Most state-of-the-art works have addressed the challenge by aggregating group members’ personal preferences to learn the group representation. However, the representation learning for a group is most complex beyond the aggregation or fusion of group member representation, as the personal preferences and group preferences may be in different spaces and even orthogonal. In addition, the learned user representation is not accurate due to the sparsity of users’ interaction data. Moreover, the group similarity in terms of common group members has been overlooked, which, however, has the great potential to improve the group representation learning. In this work, we focus on addressing the aforementioned challenges in the group representation learning task, and devise a hierarchical hyperedge embedding-based group recommender, namely HyperGroup. Specifically, we propose to leverage the user-user interactions to alleviate the sparsity issue of user-item interactions, and design a graph neural network-based representation learning network to enhance the learning of individuals’ preferences from their friends’ preferences, which provides a solid foundation for learning groups’ preferences. To exploit the group similarity (i.e., overlapping relationships among groups) to learn a more accurate group representation from highly limited group-item interactions, we connect all groups as a network of overlapping sets (a.k.a. hypergraph), and treat the task of group preference learning as embedding hyperedges (i.e., user sets/groups) in a hypergraph, where an inductive hyperedge embedding method is proposed. To further enhance the group-level preference modeling, we develop a joint training strategy to learn both user-item and group-item interactions in the same process. We conduct extensive experiments on two real-world datasets, and the experimental results demonstrate the superiority of our proposed HyperGroup in comparison to the state-of-the-art baselines.

Order matters: sleep spindles contribute to memory consolidation only when followed by rapid-eye-movement sleep

Sleep is known to benefit memory consolidation, but little is known about the contribution of sleep stages within the sleep cycle. The sequential hypothesis proposes that memories are first replayed during non-rapid-eye-movement (NREM or N) sleep and then integrated into existing networks during rapid-eye-movement (REM or R) sleep, two successive critical steps for memory consolidation. However, it lacks experimental evidence as N always precedes R sleep in physiological conditions. We tested this sequential hypothesis in patients with central hypersomnolence disorder, including patients with narcolepsy who present the unique, anti-physiological peculiarity of frequently falling asleep in R sleep before entering N sleep. Patients performed a visual perceptual learning task before and after daytime naps stopped after one sleep cycle, starting in N or R sleep and followed by the other stage (i.e. N-R vs. R-N sleep sequence). We compared over-nap changes in performance, reflecting memory consolidation, depending on the sleep sequence during the nap. Thirty-six patients who slept for a total of 67 naps were included in the analysis. Results show that sleep spindles are associated with memory consolidation only when N is followed by R sleep, that is in physiologically ordered N-R naps, thus providing support to the sequential hypothesis in humans. In addition, we found a negative effect of rapid-eye-movements in R sleep on perceptual consolidation, highlighting the complex role of sleep stages in the balance to remember and to forget.

Explaining Valence Asymmetries in Value Learning: A Reinforcement Learning Account

To understand how acquired value impacts how we perceive and process stimuli, psychologists have developed the Value Learning Task (VLT; e.g., Raymond & O’Brien, 2009). The task consists of a series of trials in which participants attempt to maximize accumulated winnings as they make choices from a pair of presented images associated with probabilistic win, loss, or no-change outcomes. Despite the task having a symmetric outcome structure for win and loss pairs, people learn win associations better than loss associations (Lin, Cabrera-Haro, & Reuter-Lorenz, 2020). This asymmetry could lead to differences when the stimuli are probed in subsequent tasks, compromising inferences about how acquired value affects downstream processing. We investigate the nature of the asymmetry using a standard error-driven reinforcement learning model with a softmax choice rule. Despite having no special role for valence, the model yields the asymmetry observed in human behavior, whether the model parameters are set to maximize empirical fit, or task payoff. The asymmetry arises from an interaction between a neutral initial value estimate and a choice policy that exploits while exploring, leading to more poorly discriminated value estimates for loss stimuli. We also show how differences in estimated individual learning rates help to explain individual differences in the observed win-loss asymmetries, and how the final value estimates produced by the model provide a simple account of a post-learning explicit value categorization task.

Improving Road Surface Area Extraction via Semantic Segmentation with Conditional Generative Learning for Deep Inpainting Operations

The road surface area extraction task is generally carried out via semantic segmentation over remotely-sensed imagery. However, this supervised learning task is often costly as it requires remote sensing images labelled at the pixel level, and the results are not always satisfactory (presence of discontinuities, overlooked connection points, or isolated road segments). On the other hand, unsupervised learning does not require labelled data and can be employed for post-processing the geometries of geospatial objects extracted via semantic segmentation. In this work, we implement a conditional Generative Adversarial Network to reconstruct road geometries via deep inpainting procedures on a new dataset containing unlabelled road samples from challenging areas present in official cartographic support from Spain. The goal is to improve the initial road representations obtained with semantic segmentation models via generative learning. The performance of the model was evaluated on unseen data by conducting a metrical comparison where a maximum Intersection over Union (IoU) score improvement of 1.3% was observed when compared to the initial semantic segmentation result. Next, we evaluated the appropriateness of applying unsupervised generative learning using a qualitative perceptual validation to identify the strengths and weaknesses of the proposed method in very complex scenarios and gain a better intuition of the model’s behaviour when performing large-scale post-processing with generative learning and deep inpainting procedures and observed important improvements in the generated data.

EXPRESS: Are animates special? Exploring the effects of selective attention and animacy on visual statistical learning

Our visual system is built to extract regularities in how objects within our visual environment appear in relation to each other across time and space (‘visual statistical learning’). Existing research indicates that visual statistical learning is modulated by selective attention. Our attentional system prioritises information that enables behaviour; for example, animates are prioritised over inanimates (the ‘animacy advantage’). The present study examined the effects of selective attention and animacy on visual statistical learning in young adults (N = 284). We tested visual statistical learning of attended and unattended information across four animacy conditions: (i) living things that can self-initiate movement (animals); (ii) living things that cannot self-initiate movement (fruits and vegetables); (iii) non-living things that can generate movement (vehicles); and (iv) non-living things that cannot generate movement (tools and kitchen utensils). We implemented a four-point confidence-rating scale as an assessment of participants’ awareness of the regularities in the visual statistical learning task. There were four key findings. First, selective attention plays a critical role by modulating visual statistical learning. Second, animacy does not play a special role in visual statistical learning. Third, visual statistical learning of attended information cannot be exclusively accounted for by unconscious knowledge. Fourth, performance on the visual statistical learning task is associated with the proportion of stimuli that were named or labelled. Our findings support the notion that visual statistical learning is a powerful mechanism by which our visual system resolves an abundance of sensory input over time.

Averting the next credibility crisis in psychological science: Within-person methods for personalized diagnostics and intervention.

Personalizing assessments, predictions, and treatments of individuals is currently a defining trend in psychological research and applied fields, including personalized learning, personalized medicine, and personalized advertisement. For instance, the recent pandemic has reminded parents and educators of how challenging yet crucial it is to get the right learning task to the right student at the right time. Increasingly, psychologists and social scientists are realizing that the between- person methods that we have long relied upon to describe, predict, and treat individuals may fail to live up to these tasks (e.g., Molenaar, 2004). Consequently, there is a risk of a credibility loss, possibly similar to the one seen during the replicability crisis (Ioannides, 2005), because we have only started to understand how many of the conclusions that we tend to draw based on between-person methods are based on a misunderstanding of what these methods can tell us and what they cannot. An imminent methodological revolution will likely lead to a change of even well-established psychological theories (Barbot et al., 2020). Fortunately, methodological solutions for personalized descriptions and predictions, such as many within-person analyses, are available and undergo rapid development, although they are not yet embraced in all areas of psychology, and some come with their own limitations. This article first discusses the extent of the theory-method gap, consisting of theories about within-person patterns being studied with between-person methods in psychology, and the potential loss of trust that might follow from this theory-method gap. Second, this article addresses advantages and limitations of available within- person methods. Third, this article discusses how within-person methods may help improving the individual descriptions and predictions that are needed in many applied fields that aim for tailored individual solutions, including personalized learning and personalized medicine.

Achieving 90% In Data-Centric Industry Deep Learning Task

In industry deep learning application, our manually labeled data has a certain number of noisy data. To solve this problem and achieve more than 90 score in dev dataset, we present a simple method to find the noisy data and re-label the noisy data by human, given the model predictions as references in human labeling. In this paper, we illustrate our idea for a broad set of deep learning tasks, includes classification, sequence tagging, object detection, sequence generation, click-through rate prediction. The experimental results and human evaluation results verify our idea.

Modeling student engagement using optimal control theory

<p style='text-indent:20px;'>Student engagement in learning a prescribed body of knowledge can be modeled using optimal control theory, with a scalar state variable representing mastery, or self-perceived mastery, of the material and control representing the instantaneous cognitive effort devoted to the learning task. The relevant costs include emotional and external penalties for incomplete mastery, reduced availability of cognitive resources for other activities, and psychological stresses related to engagement with the learning task. Application of Pontryagin's maximum principle to some simple models of engagement yields solutions of the synthesis problem mimicking familiar behaviors including avoidance, procrastination, and increasing commitment in response to increasing mastery.</p>

Application of English Vocabulary Presentation Based on Clustering in College English Teaching

As the most basic element in English learning, vocabulary has always been the focus of teaching in college English classes, but the teaching effect is often unsatisfactory. In this paper, the genetic algorithm fitness function design part is integrated with the K-medoids algorithm to form K-GA-medoids, and secondly, it is combined with KNN to form an algorithmic framework for English vocabulary classification. In the classification process, clustering and classification steps are taken to realize the reduction of the training set samples and thus reduce the computational overhead. The experiments show that K-GA-medoids have significantly improved the clustering effect compared with traditional K-medoids, and the combination of K-GA-medoids and KNNs has effectively improved the efficiency of English vocabulary classification compared with the traditional KNN algorithm, while ensuring the classification accuracy. We found that students in college English course consider word memorization as a difficult learning task, and the traditional vocabulary teaching methods are not very effective, and the knowledge of etymology is often little known and rarely covered in classroom lectures. Therefore, the article explores new ideas and strategies for teaching vocabulary in college English from the perspective of etymology.