Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Inductive Cognitive Diagnosis for Fast Student Learning in Web-Based Online Intelligent Education Systems

Shuo Liu, Junhao Shen, Hong Qian, Aimin Zhou

TL;DR

This work tackles the challenge of inductive cognitive diagnosis in web-based open learning systems where new students continuously appear. It introduces ICDM, which builds a student-centered graph (SCG) and applies a construction-aggregation-generation-transformation (CAGT) pipeline to produce inductive mastery representations without retraining. A global-level interaction function (GLIF) integrates concept-level information, yielding fast, scalable inference for unseen students while maintaining competitive predictive performance and improvedMas consistency across four real-world datasets. The approach enables immediate, scalable feedback in WOIESs and broadens the applicability of graph-based cognitive diagnosis models to open-world educational settings.

Abstract

Cognitive diagnosis aims to gauge students' mastery levels based on their response logs. Serving as a pivotal module in web-based online intelligent education systems (WOIESs), it plays an upstream and fundamental role in downstream tasks like learning item recommendation and computerized adaptive testing. WOIESs are open learning environment where numerous new students constantly register and complete exercises. In WOIESs, efficient cognitive diagnosis is crucial to fast feedback and accelerating student learning. However, the existing cognitive diagnosis methods always employ intrinsically transductive student-specific embeddings, which become slow and costly due to retraining when dealing with new students who are unseen during training. To this end, this paper proposes an inductive cognitive diagnosis model (ICDM) for fast new students' mastery levels inference in WOIESs. Specifically, in ICDM, we propose a novel student-centered graph (SCG). Rather than inferring mastery levels through updating student-specific embedding, we derive the inductive mastery levels as the aggregated outcomes of students' neighbors in SCG. Namely, SCG enables to shift the task from finding the most suitable student-specific embedding that fits the response logs to finding the most suitable representations for different node types in SCG, and the latter is more efficient since it no longer requires retraining. To obtain this representation, ICDM consists of a construction-aggregation-generation-transformation process to learn the final representation of students, exercises and concepts. Extensive experiments across real-world datasets show that, compared with the existing cognitive diagnosis methods that are always transductive, ICDM is much more faster while maintains the competitive inference performance for new students.

Inductive Cognitive Diagnosis for Fast Student Learning in Web-Based Online Intelligent Education Systems

TL;DR

This work tackles the challenge of inductive cognitive diagnosis in web-based open learning systems where new students continuously appear. It introduces ICDM, which builds a student-centered graph (SCG) and applies a construction-aggregation-generation-transformation (CAGT) pipeline to produce inductive mastery representations without retraining. A global-level interaction function (GLIF) integrates concept-level information, yielding fast, scalable inference for unseen students while maintaining competitive predictive performance and improvedMas consistency across four real-world datasets. The approach enables immediate, scalable feedback in WOIESs and broadens the applicability of graph-based cognitive diagnosis models to open-world educational settings.

Abstract

Cognitive diagnosis aims to gauge students' mastery levels based on their response logs. Serving as a pivotal module in web-based online intelligent education systems (WOIESs), it plays an upstream and fundamental role in downstream tasks like learning item recommendation and computerized adaptive testing. WOIESs are open learning environment where numerous new students constantly register and complete exercises. In WOIESs, efficient cognitive diagnosis is crucial to fast feedback and accelerating student learning. However, the existing cognitive diagnosis methods always employ intrinsically transductive student-specific embeddings, which become slow and costly due to retraining when dealing with new students who are unseen during training. To this end, this paper proposes an inductive cognitive diagnosis model (ICDM) for fast new students' mastery levels inference in WOIESs. Specifically, in ICDM, we propose a novel student-centered graph (SCG). Rather than inferring mastery levels through updating student-specific embedding, we derive the inductive mastery levels as the aggregated outcomes of students' neighbors in SCG. Namely, SCG enables to shift the task from finding the most suitable student-specific embedding that fits the response logs to finding the most suitable representations for different node types in SCG, and the latter is more efficient since it no longer requires retraining. To obtain this representation, ICDM consists of a construction-aggregation-generation-transformation process to learn the final representation of students, exercises and concepts. Extensive experiments across real-world datasets show that, compared with the existing cognitive diagnosis methods that are always transductive, ICDM is much more faster while maintains the competitive inference performance for new students.
Paper Structure (19 sections, 10 equations, 10 figures, 6 tables)

This paper contains 19 sections, 10 equations, 10 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. METHODOLOGY: The Proposed ICDM
  5. CAGT Process
  6. Interaction Functions
  7. Model Training
  8. Experiments
  9. Experimental Settings
  10. Transductive Cognitive Diagnosis
  11. Inductive Cognitive Diagnosis
  12. Analysis of Diagnosis Results (i.e., Mas)
  13. Hyperparameters Analysis
  14. Conclusion
  15. ACKNOWLEDGEMENTS
  16. ...and 4 more sections

Figures (10)

  • Figure 1: An illustrative example of cognitive diagnosis. (a) Transductive scenario. (b) Inductive scenario.
  • Figure 2: Framework of the proposed ICDM: (a) The details of CAGT process. (b) Training and inference.
  • Figure 3: The proposed student-centered graph (SCG).
  • Figure 4: Different evaluations between transductive CD and inductive CD: (a) Transductive CD. (b) Inductive CD.
  • Figure 5: Interpretability and time results on EdNet-1 dataset.
  • ...and 5 more figures