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

2025-10-27

AI Summary

Cross-disciplinary cognitive diagnosis faces dual challenges: heterogeneous knowledge structures across disciplines and severe data sparsity in target domains, hindering effective feature extraction and limiting diagnostic accuracy. To address this, we propose TLCD—the first deep transfer learning framework specifically designed for cross-disciplinary cognitive diagnosis. TLCD jointly leverages domain-invariant features from a source (major) discipline and explicitly models cross-disciplinary knowledge associations via a knowledge-linked neural network, enabling robust knowledge alignment and shared representation learning. Its methodological innovations integrate deep neural architectures, hierarchical transfer strategies, and explicit structural modeling of domain knowledge. Extensive experiments on multi-disciplinary real-world educational datasets demonstrate that TLCD consistently outperforms state-of-the-art cognitive diagnosis models, achieving an average 8.2% AUC improvement. Notably, it delivers substantial gains in assessment accuracy under low-resource target disciplines, effectively mitigating data scarcity. TLCD establishes a novel paradigm for personalized, cross-disciplinary learning analytics.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Addressing cross-disciplinary cognitive diagnosis challenges
• Enhancing model performance using transfer learning strategies
• Accurately assessing student ability levels across disciplines

Innovation

• Combines deep learning with transfer learning
• Uses source discipline features to enhance target
• Improves cognitive diagnosis accuracy across disciplines