The article discusses the importance of Cognitive Diagnosis (CD) algorithms in online education and introduces the Adaptive Semantic-aware Graph-based Cognitive Diagnosis model (ASG-CD). The model leverages bipartite graph information to improve diagnostic performance by addressing edge heterogeneity and uncertainty. It maps students, exercises, and knowledge concepts into latent representations, utilizes Semantic-aware Graph Neural Network Layer to handle edge heterogeneity, and introduces an Adaptive Edge Differentiation Layer to filter out uncertain edges. Extensive experiments on real-world datasets demonstrate the effectiveness of ASG-CD.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Pengyang Sha... at arxiv.org 03-12-2024
https://arxiv.org/pdf/2403.05559.pdfDeeper Inquiries