EduLGCL: Local-global contrastive learning model for education recommendation

Contrastive learning has been used in recommendations to learn user and item representations from sparse and long-tail user-item interaction histories. Recommendations applied in education have several key challenges. Firstly, the frequency of student-course interactions is lower, resulting in limited data. Secondly, existing models rely on multimodal data for multi-objective recommendations and they limit the model’s generalizability. Lastly, it is important to consider the impact of static features on different students. Aiming at addressing these challenges, a novel course recommendation system based on Local-Global Contrastive Learning called as EduLGCL is proposed, in which the mutual information between course features and student features is computed to select course features. After expanding the connections, the relationship between students and courses is described from different perspectives. Multiple graph convolutional operations are performed on the interaction history graph which can connect students and courses and represent student clusters. Through the feature extraction layer, the final student representation is obtained. Extensive experiments were conducted on three public datasets and a course dataset collected from a real-world environment to validate the performance of the EduLGCL. The results demonstrate that EduLGCL outperforms baseline methods, particularly in handling user cold-start problems. Our code is available at https://github.com/mintZYJ/EduLGCL.