Adaptive Knowledge Transfer for Cross-Disciplinary Cold-Start Knowledge Tracing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Deng, Yulong, Guan, Zheng, He, Min, Wang, Xue, Liu, Jie, Li, Zheng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912727726817280
author Deng, Yulong
Guan, Zheng
He, Min
Wang, Xue
Liu, Jie
Li, Zheng
author_facet Deng, Yulong
Guan, Zheng
He, Min
Wang, Xue
Liu, Jie
Li, Zheng
contents Cross-Disciplinary Cold-start Knowledge Tracing (CDCKT) faces a critical challenge: insufficient student interaction data in the target discipline prevents effective knowledge state modeling and performance prediction. Existing cross-disciplinary methods rely on overlapping entities between disciplines for knowledge transfer through simple mapping functions, but suffer from two key limitations: (1) overlapping entities are scarce in real-world scenarios, and (2) simple mappings inadequately capture cross-disciplinary knowledge complexity. To overcome these challenges, we propose Mixed of Experts and Adversarial Generative Network-based Cross-disciplinary Cold-start Knowledge Tracing Framework. Our approach consists of three key components: First, we pre-train a source discipline model and cluster student knowledge states into K categories. Second, these cluster attributes guide a mixture-of-experts network through a gating mechanism, serving as a cross-domain mapping bridge. Third, an adversarial discriminator enforces feature separation by pulling same-attribute student features closer while pushing different-attribute features apart, effectively mitigating small-sample limitations. We validate our method's effectiveness across 20 extreme cross-disciplinary cold-start scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20009
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Knowledge Transfer for Cross-Disciplinary Cold-Start Knowledge Tracing
Deng, Yulong
Guan, Zheng
He, Min
Wang, Xue
Liu, Jie
Li, Zheng
Information Retrieval
H.1.2
Cross-Disciplinary Cold-start Knowledge Tracing (CDCKT) faces a critical challenge: insufficient student interaction data in the target discipline prevents effective knowledge state modeling and performance prediction. Existing cross-disciplinary methods rely on overlapping entities between disciplines for knowledge transfer through simple mapping functions, but suffer from two key limitations: (1) overlapping entities are scarce in real-world scenarios, and (2) simple mappings inadequately capture cross-disciplinary knowledge complexity. To overcome these challenges, we propose Mixed of Experts and Adversarial Generative Network-based Cross-disciplinary Cold-start Knowledge Tracing Framework. Our approach consists of three key components: First, we pre-train a source discipline model and cluster student knowledge states into K categories. Second, these cluster attributes guide a mixture-of-experts network through a gating mechanism, serving as a cross-domain mapping bridge. Third, an adversarial discriminator enforces feature separation by pulling same-attribute student features closer while pushing different-attribute features apart, effectively mitigating small-sample limitations. We validate our method's effectiveness across 20 extreme cross-disciplinary cold-start scenarios.
title Adaptive Knowledge Transfer for Cross-Disciplinary Cold-Start Knowledge Tracing
topic Information Retrieval
H.1.2
url https://arxiv.org/abs/2511.20009