Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on four real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.

This study aimed to identify factors influencing student engagement in online and blended courses at one Australian regional university. It applied a data science approach to learning and teaching data gathered from the learning management system used at this university. Data were collected and analysed from 23 subjects, spanning over 5500 student enrolments and 406 lecturer and tutor roles, over a five-year period. Based on a theoretical framework adapted from Community of Inquiry (CoI) framework by Garrison et al. (2000), the data were segregated into three groups for analysis: Student Engagement, Course Content and Teacher Input. The data analysis revealed a positive correlation between Student Engagement and Teacher Input, and interestingly, a negative correlation between Student Engagement and Course Content when a certain threshold was exceeded. The findings of the study offer useful suggestions for future course design, and pedagogical approaches teachers can adopt to foster student engagement.

POI recommendation can facilitate various Location-Based Social Network services. Existing methods generally assume the available POI check-ins are the ground-truth depiction of user behaviors. However, in real scenarios, check-in data can be rather unreliable due to both subjective and objective causes including positioning errors and user privacy concerns. The data uncertainty issue may lead to significant negative impacts on POI recommendation, but has not been fully explored. To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of user check-ins, and propose a Bayes-enhanced Multi-view Attention Network to effectively address it. Specifically, we construct three POI graphs to comprehensively model the dependencies among the POIs from different views, including the personal POI transition graph, the semantic-based and distance-based POI graphs. As the personal graph is usually sparse and sensitive to noise, we design a Bayes-enhanced spatial dependency learning module for data augmentation from the local view. A Bayesian posterior guided graph augmentation approach is adopted to generate a new graph with collaborative signals to increase the data diversity and thus counteract the data uncertainty issue. Next, a multi-view attention-based user preference learning module is proposed. By incorporating the semantic and distance correlations of POIs, the user preference can be effectively refined and finally achieve robust recommendations. We conduct extensive experiments over three datasets. The results show that our proposal significantly outperforms the state-of-the-art methods in POI recommendation when the available check-ins are incomplete and noisy.

Dynamic graphs refer to graphs whose structure dynamically changes over time. Despite the benefits of learning vertex representations (i.e., embeddings) for dynamic graphs, existing works merely view a dynamic graph as a sequence of changes within the vertex connections, neglecting the crucial asynchronous nature of such dynamics where the evolution of each local structure starts at different times and lasts for various durations. To maintain asynchronous structural evolutions within the graph, we innovatively formulate dynamic graphs as temporal edge sequences associated with joining time of vertices (ToV) and timespan of edges (ToE). Then, a time-aware Transformer is proposed to embed vertices’ dynamic connections and ToEs into the learned vertex representations. Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information. Extensive evaluations on several datasets show that our approach outperforms the state-of-the-art in a wide range of graph mining tasks. At the same time, it is very efficient and scalable for embedding large-scale dynamic graphs.