Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks
This work addresses a fundamental task in AI for education, but it is incremental as it improves upon existing GNN methods for a specific domain.
The paper tackled the problem of concept prerequisite relation prediction (CPRP) in AI for education by proposing a permutation-equivariant directed graph neural network model, which achieved better prediction performance than state-of-the-art methods on three public datasets.
This paper studies the problem of CPRP, concept prerequisite relation prediction, which is a fundamental task in using AI for education. CPRP is usually formulated into a link-prediction task on a relationship graph of concepts and solved by training the graph neural network (GNN) model. However, current directed GNNs fail to manage graph isomorphism which refers to the invariance of non-isomorphic graphs, reducing the expressivity of resulting representations. We present a permutation-equivariant directed GNN model by introducing the Weisfeiler-Lehman test into directed GNN learning. Our method is then used for CPRP and evaluated on three public datasets. The experimental results show that our model delivers better prediction performance than the state-of-the-art methods.