ProPRL: Property-Aware Prerequisite Relation Learning in Educational Knowledge Graphs

2026-08-03

AI Summary

This work addresses the limitations of existing prerequisite relation learning methods, which often reduce the task to standard link prediction and struggle to adaptively integrate multi-source educational evidence while frequently yielding contradictory bidirectional predictions. To overcome these issues, we propose ProPRL, a novel framework that constructs a concept-resource hypergraph and a directed learning behavior graph to capture complementary representations. ProPRL employs a pairwise conditional gating mechanism for adaptive fusion of the two views and incorporates an irreversibility constraint to reinforce directional modeling of prerequisite relations. By integrating hypergraph neural networks, a direction-preserving personalized propagation scheme, and antisymmetric regularization, our approach achieves state-of-the-art performance, significantly outperforming existing methods across multiple real-world educational datasets.

Abstract

Prerequisite relation learning is central to adaptive instruction, yet existing methods often formulate it as conventional link prediction, limiting their ability to adaptively integrate complementary educational evidence for individual candidate pairs and to discourage contradictory reverse predictions. We propose ProPRL, a Property-aware Prerequisite Relation Learning framework. ProPRL first learns complementary concept representations from a concept-resource hypergraph and a directed learning-behavior graph, where direction-preserving personalized propagation aggregates multi-hop behavioral evidence. It then employs a Pair-conditioned Gate to adaptively weight and fuse the two views for each candidate ordered concept pair. Finally, an \textit{Irreversibility Constraint} introduces an anti-symmetry regularizer that penalizes simultaneously high confidence in both directions of the same concept pair. Experiments on multiple real-world educational datasets show that ProPRL achieves state-of-the-art performance on prerequisite relation learning.

Problem

• prerequisite relation learning
• educational knowledge graphs
• link prediction
• concept representation
• irreversibility

Innovation

• Prerequisite Relation Learning
• Property-aware Representation
• Direction-preserving Propagation
• Pair-conditioned Gate
• Irreversibility Constraint