Qinyi Liu

The expansion of large-scale online education platforms has yielded vast amounts of student interaction data for knowledge tracing (KT). KT models estimate students’ concept mastery from interaction data, but the models’ performance is sensitive to input data quality. Gaming behaviors, such as excessive hint use, may misrepresent students’ knowledge and undermine model reliability. However, systematic investigations of how different types of gaming behaviors affect KT remain scarce, and existing studies rely on costly manual analysis that does not capture behavioral diversity. In this study, we conceptualize gaming behaviors as a form of data poisoning, defined as the deliberate submission of incorrect or misleading interaction data to corrupt a model’s learning process. We design Data Poisoning Attacks (DPA) to simulate diverse gaming patterns and systematically evaluate their impact on KT model performance. Moreover, drawing on advances in DPA detection, we explore unsupervised approaches to enhance the generalizability of gaming behavior detection. We find that KT models performance tend to decrease especially for random guess behaviors. Our findings provide insights into the vulnerabilities of KT models and highlight the potential of adversarial methods for improving the robustness of learning analytics systems.

Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer high predictive accuracy in real-world tasks. However, the fairness properties of these foundational models, which incorporate ideas from causal reasoning during pre-training, remain underexplored. In this work, we conduct a comprehensive empirical evaluation of TabPFN and its fine-tuned variants, assessing predictive performance, fairness, and robustness across varying dataset sizes and distributional shifts. Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines and exhibits robustness to spurious correlations, improvements in fairness are moderate and inconsistent, particularly under missing-not-at-random (MNAR) covariate shifts. These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness, highlighting implications for deploying TabPFN (and similar) models in practice and the need for further fairness interventions.

Synthetic Data Generation (SDG) can be used to facilitate privacy-preserving data sharing. However, most existing research focuses on privacy attacks where the adversary is the recipient of the released synthetic data and attempts to infer sensitive information from it. This study investigates quality degradation attacks initiated by adversaries who possess access to the real dataset or control over the generation process, such as the data owner, the synthetic data provider, or potential intruders. We formalize a corresponding threat model and empirically evaluate the effectiveness of targeted manipulations of real data (e.g., label flipping and feature-importance-based interventions) on the quality of generated synthetic data. The results show that even small perturbations can substantially reduce downstream predictive performance and increase statistical divergence, exposing vulnerabilities within SDG pipelines. This study highlights the need to integrate integrity verification and robustness mechanisms, alongside privacy protection, to ensure the reliability and trustworthiness of synthetic data sharing frameworks.

Undergraduate mathematics education is essential for building a foundation for success in various scientific disciplines. Curriculum reforms in mathematics education have emphasized the need for cultivating learning skills that depend on effective student engagement (SE). Consequently, there has been growing research on the mechanisms that facilitate SE and promote its development. To gain insights into the state of SE research in undergraduate mathematics, the current systematic review addresses the varied research by examining four key aspects: a) theoretical grounding and research aims, b) definitions, c) measurement, and d) learning outcomes. Following the PRISMA guidelines, a literature search identified 1,584 records, with 48 papers meeting the inclusion criteria. The findings reveal three primary research aims and three approaches to grounding SE research, with most studies using an instruction-focused framework to evaluate instructional methods. Nearly half of the papers provided a definition of SE, with analysis showing varied uses of elements like psychological investment and multidimensionality. Studies that used multiple elements offered more concise definitions. Measurement of SE predominantly focused on online learning through log files or course participation via self-reports, with behavioral engagement being the most commonly examined dimension. Less than half of the studies explored the relationship between SE and learning outcomes, using both variable-oriented and person-oriented approaches to examine this connection. Based on the current findings, the review offers recommendations for aligning conceptualizations, definitions, measurement, and context in future research to foster a shared understanding and guide interventions.

The increasing adoption of data-driven applications in education such as in learning analytics and AI in education has raised significant privacy and data protection concerns. While these challenges have been widely discussed in previous works, there are still limited practical solutions. Federated learning has recently been discoursed as a promising privacy-preserving technique, yet its application in education remains scarce. This paper presents an experimental evaluation of federated learning for educational data prediction, comparing its performance to traditional non-federated approaches. Our findings indicate that federated learning achieves comparable predictive accuracy. Furthermore, under adversarial attacks, federated learning demonstrates greater resilience compared to non-federated settings. We summarise that our results reinforce the value of federated learning as a potential approach for balancing predictive performance and privacy in educational contexts.

Supporting learning and teaching at scale requires access to large and high‐quality content and datasets for analysis and innovation. With rapid advances in artificial intelligence (AI) and the growing demand for data, synthetic data has emerged as a potential solution for addressing these challenges. This editorial introduces the contributions of five accepted articles to the special section AI for Synthetic Data Generation in Education: Scaling Teaching and Learning. These articles explore key themes in leveraging AI‐generated synthetic data to support learning and teaching as well as enhance educational practices at scale. The editorial emphasizes that hybrid strategies that leverage AI alongside human judgment are essential for scaling support for learning and teaching through synthetic data generation.