TLCD: A Deep Transfer Learning Framework for Cross-Disciplinary Cognitive Diagnosis

TL;DR

This paper tackles cross-disciplinary cognitive diagnosis by integrating deep neural cognitive diagnosis models with transfer learning to reuse knowledge across disciplines. It introduces TLCD, built around NeuralCD and KaNCD architectures, and implements three-stage pipelines: vector embedding, pre-training on main subjects, and transfer learning to target disciplines. Experiments on the YNEG dataset across 8 subjects demonstrate that transfer learning improves predictive accuracy (AUC, ACC) and error metrics (RMSE, MAE) compared to in-domain baselines, with KaNCD-based transfer yielding particularly strong gains in both science and humanities domains. The work highlights the practical impact of cross-disciplinary diagnostic ability for personalized education and suggests avenues for further transfer strategies and evaluation in diverse knowledge domains.

Abstract

Driven by the dual principles of smart education and artificial intelligence technology, the online education model has rapidly emerged as an important component of the education industry. Cognitive diagnostic technology can utilize students' learning data and feedback information in educational evaluation to accurately assess their ability level at the knowledge level. However, while massive amounts of information provide abundant data resources, they also bring about complexity in feature extraction and scarcity of disciplinary data. In cross-disciplinary fields, traditional cognitive diagnostic methods still face many challenges. Given the differences in knowledge systems, cognitive structures, and data characteristics between different disciplines, this paper conducts in-depth research on neural network cognitive diagnosis and knowledge association neural network cognitive diagnosis, and proposes an innovative cross-disciplinary cognitive diagnosis method (TLCD). This method combines deep learning techniques and transfer learning strategies to enhance the performance of the model in the target discipline by utilizing the common features of the main discipline. The experimental results show that the cross-disciplinary cognitive diagnosis model based on deep learning performs better than the basic model in cross-disciplinary cognitive diagnosis tasks, and can more accurately evaluate students' learning situation.

Figures (8)

• Figure 1: An instance-based approach to transfer learning.
• Figure 2: Isomorphic Transfer Learning vs. Heteromorphic Transfer Learning.
• Figure 3: Cross-disciplinary cognitive diagnostic model.
• Figure 4: Vector embedding based on KaNCD transfer learning.
• Figure 5: Scatter plot of transfer learning model optimized based on NeuralCD model for predicting answers in science subjects.