Graph Continual Learning for Incremental Cognitive Diagnosis
ACM Transactions on Intelligent Systems and Technology · 21.11.2026
DOI: 10.1145/3864050 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 21.11.2026. Verfasst von Fei Liu und 7 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben.
Abstract (Originalsprache)
Cognitive diagnosis (CD) aims to model students’ evolving cognitive states by learning representations of students, exercises, and knowledge concepts. Graph-based CD models (Graph-CDMs) enhance representation learning by capturing high-order relationships within interaction graphs. However, existing Graph-CDMs struggle with challenges arising from data distribution shifts and cascading effects in dynamic graph scenarios, limiting their real-world applicability. To tackle these limitations, we propose Continual Learning for Incremental Cognitive Diagnosis (GRACE), a continual learning framework for dynamic Graph-CDMs. GRACE disentangles node embeddings into stage-unique and cross-stage-generic components to localize updates and suppress graph cascade effects. To address distributional shifts, it incorporates a multi-level graph prompt mechanism—injecting node-, structure-, and temporal-level prompts—to guide adaptation while considering knowledge retention across stages. Extensive experiments on three real-world datasets demonstrate the superior performance, robustness, and adaptability of GRACE compared to traditional full-training and fine-tuning baselines across various Graph-CDMs.
Zitieren
APA
Liu, F., Xie, T., Xia, C., Zhou, H., Ji, S., Yang, Y., Li, X., & Wu, L. (2026). Graph Continual Learning for Incremental Cognitive Diagnosis. ACM Transactions on Intelligent Systems and Technology. https://doi.org/10.1145/3864050
Vancouver
Liu F, Xie T, Xia C, Zhou H, Ji S, Yang Y, et al. Graph Continual Learning for Incremental Cognitive Diagnosis. ACM Transactions on Intelligent Systems and Technology. 2026. doi:10.1145/3864050
BibTeX
@article{Liu2026,
author = {Liu, Fei and Xie, Tong and Xia, Chenao and Zhou, Haowei and Ji, Shengwei and Yang, Yonghui and Li, Xin and Wu, Le},
title = {Graph Continual Learning for Incremental Cognitive Diagnosis},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2026},
doi = {10.1145/3864050}
}
EUVIMED