arXiv subjects

Amel Bouzeghoub

Publications and source records attributed to Amel Bouzeghoub.

3 recordsLinked to original sources

arXiv2026

RegKT: Interpretable and Robust Deep Knowledge Tracing With IRT-Regularizer

As deep learning models continue to advance, knowledge tracing models have achieved higher accuracy. However, these gains come at the cost of reduced interpretability, which is crucial for practitioners in educational settings to adopt new methodologies. Additionally, deep learning models are prone to overfitting, particularly when dealing with the small datasets that are common in educational applications. In this paper, we propose a novel regularization technique designed to enhance the robustness of deep-learning-based knowledge tracing models, while simultaneously improving their interpretability. Our method addresses both the interpretability and overfitting challenges, making it more feasible for real-world educational applications.

cs.LG↗

arXiv2026

Counterfactual learning of new adaptive instructional policies using logged data

Optimizing instructional policies in Intelligent Tutoring Systems (ITS) typically requires costly online experimentation or student simulators that may fail to capture real-world dynamics. This paper introduces an offline contextual bandit framework that learns new adaptive policies directly from logged interaction data. By mapping student-item interactions onto a continuous latent proficiency-difficulty scale using a Rasch model, we cast the tutoring process as a continuous stochastic bandit problem. We propose a novel reward function designed to optimize ''flow'' by balancing task challenge with student success. Our approach includes a round-specific behavior policy estimation that serves as both a propensity model for off-policy evaluation and a diagnostic tool for ITS adaptivity. We demonstrate the efficacy of this framework across four large-scale real-world datasets, achieving consistent policy improvements over the logged behavior policy. The results show that effective instructional policies can be learned and visualized within seconds of computation, providing a scalable path for improving adaptive learning systems without further data collection.

cs.LG↗

arXiv2024

TIMBRE: Efficient Job Recommendation On Heterogeneous Graphs For Professional Recruiters

Job recommendation gathers many challenges well-known in recommender systems. First, it suffers from the cold start problem, with the user (the candidate) and the item (the job) having a very limited lifespan. It makes the learning of good user and item representations hard. Second, the temporal aspect is crucial: We cannot recommend an item in the future or too much in the past. Therefore, using solely collaborative filtering barely works. Finally, it is essential to integrate information about the users and the items, as we cannot rely only on previous interactions. This paper proposes a temporal graph-based method for job recommendation: TIMBRE (Temporal Integrated Model for Better REcommendations). TIMBRE integrates user and item information into a heterogeneous graph. This graph is adapted to allow efficient temporal recommendation and evaluation, which is later done using a graph neural network. Finally, we evaluate our approach with recommender system metrics, rarely computed on graph-based recommender systems.

cs.IR↗