RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems

Gao, Weibo; Liu, Qi; Huang, Zhenya; Yin, Yan; Bi, Haoyang; Wang, Mu‐Chun; Ma, Jinghong; Wang, Shijin; Su, Yu

doi:10.1145/3404835.3462932

Cited by 74 publications

(42 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…prerequisite) [29]. The relation graph, as a type of knowledge graph, has been used in many fields with various graph representation learning [13,21,28]. For example, GKT [28] uses Graph Neural Network (GNN) [31] with a graph-like knowledge structure for knowledge tracing.…”

Section: Knowledge Graphmentioning

confidence: 99%

“…For example, GKT [28] uses Graph Neural Network (GNN) [31] with a graph-like knowledge structure for knowledge tracing. RCD [13] uses Graph Attention Network (GAT) [37] to aggregate multi-level information for cognitive diagnosis and CSEAL [21] designs a graph-based cognitive navigation for adaptive learning. To our best knowledge, we are the first to involve the relation graph in the CAT setting.…”

Section: Knowledge Graphmentioning

confidence: 99%

See 1 more Smart Citation

GMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing

Wang

Long

Yin

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Computerized Adaptive Testing (CAT) refers to an online system that adaptively selects the best-suited question for students with various abilities based on their historical response records. Compared with traditional CAT methods based on heuristic rules, recent data-driven CAT methods obtain higher performance by learning from large-scale datasets. However, most CAT methods only focus on the quality objective of predicting the student ability accurately, but neglect concept diversity or question exposure control, which are important considerations in ensuring the performance and validity of CAT. Besides, the students' response records contain valuable relational information between questions and knowledge concepts. The previous methods ignore this relational information, resulting in the selection of sub-optimal test questions. To address these challenges, we propose a Graph-Enhanced Multi-Objective method for CAT (GMOCAT). Firstly, three objectives, namely quality, diversity and novelty, are introduced into the Scalarized Multi-Objective Reinforcement Learning framework of CAT, which respectively correspond to improving the prediction accuracy, increasing the concept diversity and reducing the question exposure. We use an Actor-Critic Recommender to select questions and optimize three objectives simultaneously by the scalarization function. Secondly, we utilize the graph neural network to learn relation-aware embeddings of questions and concepts. These embeddings are able

show abstract

Section: Knowledge Graphmentioning

confidence: 99%

Section: Knowledge Graphmentioning

confidence: 99%

GMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing

Wang

Long

Yin

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…The complexity of student's behavior in the CAT is mainly reflected in guess and slip factors (Vie et al 2017;Liu et al 2018;Gao et al 2021): For example, when faced with a multiple-choice question with 4 options, even if the student doesn't master it, there is a 25% chance of answering it correctly (i.e., guess factor); When faced with a simple one, there may be a small chance (e.g., 5%) to answer it wrong (i.e., slip factor). In order to achieve the ultimate goal of CAT, i.e., measuring the true proficiency level of student, the selection algorithm should identify and eliminate these perturbations in her performance for better selection.…”

Section: Contradiction Learningmentioning

confidence: 99%

Fully Adaptive Framework: Neural Computerized Adaptive Testing for Online Education

Zhuang

Liu

Huang

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

Computerized Adaptive Testing (CAT) refers to an efficient and personalized test mode in online education, aiming to accurately measure student proficiency level on the required subject/domain. The key component of CAT is the "adaptive" question selection algorithm, which automatically selects the best suited question for student based on his/her current estimated proficiency, reducing test length. Existing algorithms rely on some manually designed and pre-fixed informativeness/uncertainty metrics of question for selections, which is labor-intensive and not sufficient for capturing complex relations between students and questions. In this paper, we propose a fully adaptive framework named Neural Computerized Adaptive Testing (NCAT), which formally redefines CAT as a reinforcement learning problem and directly learns selection algorithm from real-world data. Specifically, a bilevel optimization is defined and simplified under CAT's application scenarios to make the algorithm learnable. Furthermore, to address the CAT task effectively, we tackle it as an equivalent reinforcement learning problem and propose an attentive neural policy to model complex non-linear interactions. Extensive experiments on real-world datasets demonstrate the effectiveness and robustness of NCAT compared with several state-of-the-art methods.

show abstract

“…Cognitive diagnosis is another fundamental issue in intelligent educational settings which aims to diagnose students' knowledge proficiency. Gao et al [31] proposed a novel relation map-driven cognitive diagnosis (RCD) framework which unifies modeling interactive and structural relations through a multi-layer student-exercise-concept map. Mao et al [32] proposed a learning behavior-aware cognitive diagnosis (LCD) framework for students' cognitive modeling with both learning behavior records and exercise records, where GCN is used to automatically refine the feature vectors representing exercises and videos.…”

Section: Graph Neural Network' Application In Educationmentioning

confidence: 99%

Study-GNN: A Novel Pipeline for Student Performance Prediction Based on Multi-Topology Graph Neural Networks

Wang

et al. 2022

Sustainability

View full text Add to dashboard Cite

Student performance prediction has attracted increasing attention in the field of educational data mining, or more broadly, intelligent education or “AI + education”. Accurate performance prediction plays a significant role in solving the problem of a student dropping out, promoting personalized learning and improving teaching efficiency, etc. Traditional student performance prediction methods usually ignore the potential (underlying) relationship among students. In this paper, we use graph structure to reflect the students’ relationships and propose a novel pipeline for student performance prediction based on newly-developed multi-topology graph neural networks (termed MTGNN). In particular, we propose various ways for graph construction based on similarity learning using different distance metrics. Based on the multiple graphs of different topologies, we design an MTGNN module, as a key module in the pipeline, to deal with the semi-supervised node classification problem where each node represents a student (and the node label is the student’s performance, e.g., Pass/Fail/Withdrawal). An attention-based method is developed to produce the unified graph representation in MTGNN. The effectiveness of the proposed pipeline is verified in a case study, where a real-world educational dataset and several existing approaches are used for performance comparison. The experiment results show that, compared with some traditional machine learning methods and the vanilla graph convolutional network with only a single graph topology, our proposed pipeline works effectively and favorably in student performance prediction.

show abstract

RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems

Cited by 74 publications

References 31 publications

GMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing

GMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing

Fully Adaptive Framework: Neural Computerized Adaptive Testing for Online Education

Study-GNN: A Novel Pipeline for Student Performance Prediction Based on Multi-Topology Graph Neural Networks

Contact Info

Product

Resources

About