---
title: "Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis"
authors:
  - "Jingwei Qu"
  - "Mingze Zhang"
  - "Pingshun Zhang"
  - "Li Tao"
  - "Ying Wang"
  - "Zhaofang Yang"
  - "Haibin Ling"
doi: "10.24963/ijcai.2026/333"
url: "https://ijcai.org/proceedings/2026/333"
pdf: "https://ijcai.org/proceedings/2026/0333.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2997-3005"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Education"
  - "Data Mining: Mining graphs"
---

# 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

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2997-3005. DOI: [10.24963/ijcai.2026/333](https://doi.org/10.24963/ijcai.2026/333)

## 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.