Knowledge tracing (KT) aims to monitor students' evolving knowledge states through their learning interactions with concept-related questions, and can be indirectly evaluated by predicting how students will perform on future questions. In this paper, we observe that there is a common phenomenon of answer bias, i.e., a highly unbalanced distribution of correct and incorrect answers for each question. Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students' knowledge states. To address this issue, we approach the KT task from a causality perspective. A causal graph of KT is first established, from which we identify that the impact of answer bias lies in the direct causal effect of questions on students' responses. A novel COunterfactual REasoning (CORE) framework for KT is further proposed, which separately captures the total causal effect and direct causal effect during training, and mitigates answer bias by subtracting the latter from the former in testing. The CORE framework is applicable to various existing KT models, and we implement it based on the prevailing DKT, DKVMN, and AKT models, respectively. Extensive experiments on three benchmark datasets demonstrate the effectiveness of CORE in making the debiased inference for KT. We have released our code at https://github.com/lucky7-code/CORE.

Academic performance prediction aims to leverage student-related information to predict their future academic outcomes, which is beneficial to numerous educational applications, such as personalized teaching and academic early warning. In this article, we reveal the students' behavior trajectories by mining campus smartcard records, and capture the characteristics inherent in trajectories for academic performance prediction. Particularly, we carefully design a tri-branch convolutional neural network (CNN) architecture, which is equipped with rowwise, columnwise, and depthwise convolutions and attention operations, to effectively capture the persistence, regularity, and temporal distribution of student behavior in an end-to-end manner, respectively. However, different from existing works mainly targeting at improving the prediction performance for the whole students, we propose to cast academic performance prediction as a top-k ranking problem, and introduce a top-k focused loss to ensure the accuracy of identifying academically at-risk students. Extensive experiments were carried out on a large-scale real-world dataset, and we show that our approach substantially outperforms recently proposed methods for academic performance prediction. For the sake of reproducibility, our codes have been released at https://github.com/ZongJ1111/Academic-Performance-Prediction.

Knowledge tracing aims to trace students’ evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this article, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students’ learning interactions to capture the heterogeneous exercise–concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To combine the dual graph models, we introduce the technique of online knowledge distillation. This choice arises from the observation that, while the knowledge tracing model is designed to predict students’ responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger ensemble teacher model, which provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.

Existing multi-view representation learning methods typically follow a specific-to-uniform pipeline, extracting latent features from each view and then fusing or aligning them to obtain the unified object representation. However, the manually pre-specified fusion functions and aligning criteria could potentially degrade the quality of the derived representation. To overcome them, we propose a novel uniform-to-specific multi-view learning framework from a meta-learning perspective, where the unified representation no longer involves manual manipulation but is automatically derived from a meta-learner named MetaViewer. Specifically, we formulated the extraction and fusion of view-specific latent features as a nested optimization problem and solved it by using a bi-level optimization scheme. In this way, MetaViewer automatically fuses view-specific features into a unified one and learns the optimal fusion scheme by observing reconstruction processes from the unified to the specific over all views. Extensive experimental results in downstream classification and clustering tasks demonstrate the efficiency and effectiveness of the proposed method.

Summary As human activities in mobile environments are facing an ever‐increasing range of data, it is of great research importance to explore in depth the salient features of data that discriminate human behavior patterns and socio‐demographic factors. However, human activity behavior that consists of a series of complex spatio‐temporal activity processes is difficult to model. In this article, we develop a framework to perform activity behavior pattern mining and recognition, and the proposed framework has been applied to the American Time Use Survey to explore representative activity behavior patterns and socio‐demographic factors. The main contributions are as follows: (1) A method of activity behavior similarity is presented based on daily activities and activity sequences. (2) An activity sequence similarity algorithm with is proposed by line segment tree, greedy algorithm, and dynamic programming. (3) Representative activity behavior patterns and socio‐demographic factors are derived by clustering analysis and mining. (4) The activity behavior pattern is recognized by activity behavior features or socio‐demographic features. Through the experiments, we find that different daily activity behavior patterns are associated with specific socio‐demographic factors.

Student performance prediction plays a critical role in numerous educational scenarios, e.g., academic early warning and personalized teaching. A large body of researches have been developed for better learning gains through leveraging plentiful student-related information, such as students' historical course grades and demographical data. Recent years, campus smartcards have been widely used in most of Chinese universities, and a large amount of students' behavioral data can be recorded in an unobtrusive style, which provides a new perspective for us to predict students' academic performance. Different from most of traditional approaches, in this study, we try to exploit students' campus behavioral data, and present a novel approach for student performance prediction, namely as HANDS (enHancing Academic performaNce via Deep foreSt), which introduces decision tree-based deep learning method into establishing the predictive models. Particularly, benefiting from end-to-end learning style of deep learning, the proposed HANDS method can automatically extract students' behavioral characteristics and predict their academic performance. And thus it can save expensive human labor cost, compared with handcrafted feature-based approaches. Experimental results on a real-world data set demonstrate the superiority of our approach over the state-of-the-art methods.

Student performance prediction aims to leverage student-related information to predict their future academic outcomes, which may be beneficial to numerous educational applications, such as personalized teaching and academic early warning. In this paper, we seek to address the problem by analyzing students' daily studying and living behavior, which is comprehensively recorded via campus smart cards. Different from previous studies, we propose an end-to-end student performance prediction model, namely Tri-branch CNN, which is equipped with three types of convolutional filters, i.e., the row-wise convolution, column-wise convolution, and group-wise convolution, to effectively capture the duration, periodicity, and location-aware characteristic of student behavior, respectively. We also introduce the attention mechanism and cost-sensitive learning strategy to further improve the accuracy of our approach. Extensive experiments on a large-scale real-world dataset demonstrate the potential of our approach for student performance prediction.

Aesthetics assessment and emotion recognition are two fundamental problems in user perception understanding. While the two tasks are correlated and mutually beneficial, they are usually solved separately in existing studies. In this paper, we resort to multi-task learning to deal with aesthetics assessment and emotion recognition for images in a unified framework. Towards this goal, we extend a large scale emotion dataset by further manually rating the aesthetic qualities of images. To our best knowledge, the new dataset is the first collection of images that are associated with both aesthetic and emotional labels. Besides, we present a novel Aesthetics-Emotion hybrid Network (AENet) for multi-task learning on aesthetics assessment and emotion recognition. Task-specific and shared features have been explicitly separated by different network streams, and effectively fused at multiple network levels. Experiments on our new and benchmark datasets verify the effectiveness of our approach for unified aesthetics and emotion prediction.