Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling

Weibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Hao Wang, Yin Gu, Zheng Zhang

TL;DR

Coral, a Collaborative cognitive diagnosis model with disentangled representation learning, aims to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states in the context of intelligent education.

Abstract

Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i.e., knowledge proficiency) in the context of intelligent education. The primary challenges lie in identifying implicit collaborative connections and disentangling the entangled cognitive factors of learners for improved explainability and controllability in learner Cognitive Diagnosis (CD). However, there has been no work on CD capable of simultaneously modeling collaborative and disentangled cognitive states. To address this gap, we present Coral, a Collaborative cognitive diagnosis model with disentangled representation learning. Specifically, Coral first introduces a disentangled state encoder to achieve the initial disentanglement of learners' states. Subsequently, a meticulously designed collaborative representation learning procedure captures collaborative signals. It dynamically constructs a collaborative graph of learners by iteratively searching for optimal neighbors in a context-aware manner. Using the constructed graph, collaborative information is extracted through node representation learning. Finally, a decoding process aligns the initial cognitive states and collaborative states, achieving co-disentanglement with practice performance reconstructions. Extensive experiments demonstrate the superior performance of Coral, showcasing significant improvements over state-of-the-art methods across several real-world datasets. Our code is available at https://github.com/bigdata-ustc/Coral.

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling

TL;DR

Coral, a Collaborative cognitive diagnosis model with disentangled representation learning, aims to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states in the context of intelligent education.

Abstract

Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i.e., knowledge proficiency) in the context of intelligent education. The primary challenges lie in identifying implicit collaborative connections and disentangling the entangled cognitive factors of learners for improved explainability and controllability in learner Cognitive Diagnosis (CD). However, there has been no work on CD capable of simultaneously modeling collaborative and disentangled cognitive states. To address this gap, we present Coral, a Collaborative cognitive diagnosis model with disentangled representation learning. Specifically, Coral first introduces a disentangled state encoder to achieve the initial disentanglement of learners' states. Subsequently, a meticulously designed collaborative representation learning procedure captures collaborative signals. It dynamically constructs a collaborative graph of learners by iteratively searching for optimal neighbors in a context-aware manner. Using the constructed graph, collaborative information is extracted through node representation learning. Finally, a decoding process aligns the initial cognitive states and collaborative states, achieving co-disentanglement with practice performance reconstructions. Extensive experiments demonstrate the superior performance of Coral, showcasing significant improvements over state-of-the-art methods across several real-world datasets. Our code is available at https://github.com/bigdata-ustc/Coral.

Paper Structure

This paper contains 20 sections, 27 equations, 6 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Coral
  4. Problem Setup
  5. Disentangled Cognitive Representation Encoding
  6. Collaborative Representation Learning
  7. Context-aware Collaborative Graph Learning
  8. Collaborative Graph Modeling
  9. Decoding and Reconstruction
  10. Experiments
  11. Experimental Setup
  12. Experimental Results
  13. Conclusion
  14. Proofs
  15. Algorithm
  16. ...and 5 more sections

Figures (6)

  • Figure 1: An example of human learning, where learners individually select questions to practice. Each question tests at least one knowledge concept.
  • Figure 2: The overall framework of Coral.
  • Figure 3: (a) Performance in sparse scenarios. (b) Performance under cold-start scenarios. (c) Performance with different values of $K$. (d) Disentanglement level and its correlation with performance.
  • Figure 4: (a) Selected neighbors of the target learner at different steps. (b) t-SNE visualizations of learner representations colored based on knowledge concepts.
  • Figure 5: The example of diagnosis output.
  • ...and 1 more figures

Theorems & Definitions (4)

  • proof
  • proof
  • proof
  • proof