ROME: A Graph Contrastive Multi-View Framework From Hyperbolic Angular Space for MOOCs Recommendation

Abstract

As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does not take into account the user’s learning needs with some particular subjects. However, all existing graph models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts, which may lead to biased recommendations, or by constructing improper contrasting pairs, which may result in graph noise. To overcome both challenges, we propose a g <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> aph c <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</u> ntrastive <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> ulti-view fram <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> work (ROME) from hyperbolic angular space to learn user and concept representations based on user-user and concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as different views of graph and maximize the mutual information between them. Furthermore, we maximize the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power. Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users.