Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis

Qu, Jingwei; Zhang, Mingze; Zhang, Pingshun; Tao, Li; Wang, Ying; Yang, Zhaofang; Ling, Haibin

doi:10.24963/ijcai.2026/333

Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis

Jingwei Qu, Mingze Zhang, Pingshun Zhang, Li Tao, Ying Wang, Zhaofang Yang, Haibin Ling

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2997-3005.

https://doi.org/10.24963/ijcai.2026/333

Keywords

Multidisciplinary Topics and Applications: Education
Data Mining: Mining graphs

Abstract

Cognitive diagnosis aims to infer students’ concept-level mastery from exercise response logs and exercise-concept associations. Fully leveraging heterogeneous relations and modeling large mastery-difficulty variations remain challenging, especially with a single predictor. To address these challenges, we propose RMCD, a unified cognitive diagnosis model that integrates relation-aware graph learning with Mixture-of-Experts (MoE) prediction. RMCD constructs a heterogeneous relational graph over students, exercises, and concepts with multiple relation types, and learns node and edge representations simultaneously. It derives relation-strength vectors from student-concept and exercise-concept edges to distinguish relation effects and refine node representations. RMCD further introduces an MoE-based prediction head that adaptively combines multiple expert predictors to capture diverse mastery-difficulty discrepancies. Experiments on benchmark datasets demonstrate that RMCD consistently outperforms state-of-the-art cognitive diagnosis methods. Our algorithm is available at https://github.com/swu-qjw-lab/code/tree/main/RMCD.

Jingwei Qu, Mingze Zhang, Pingshun Zhang, Li Tao, Ying Wang, Zhaofang Yang, and Haibin Ling. 2026. Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 2997–3005. https://doi.org/10.24963/ijcai.2026/333

@inproceedings{ijcai2026p333,
  title     = {Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis},
  author    = {Qu, Jingwei and Zhang, Mingze and Zhang, Pingshun and Tao, Li and Wang, Ying and Yang, Zhaofang and Ling, Haibin},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {2997--3005},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/333},
  url       = {https://doi.org/10.24963/ijcai.2026/333},
}

TY  - CPAPER
TI  - Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis
AU  - Qu, Jingwei
AU  - Zhang, Mingze
AU  - Zhang, Pingshun
AU  - Tao, Li
AU  - Wang, Ying
AU  - Yang, Zhaofang
AU  - Ling, Haibin
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 2997
EP  - 3005
DO  - 10.24963/ijcai.2026/333
UR  - https://doi.org/10.24963/ijcai.2026/333
ER  -