DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing
-
Published:2024-01-22
Issue:3
Volume:42
Page:1-24
-
ISSN:1046-8188
-
Container-title:ACM Transactions on Information Systems
-
language:en
-
Short-container-title:ACM Trans. Inf. Syst.
Author:
Cui Chaoran1ORCID,
Yao Yumo1ORCID,
Zhang Chunyun1ORCID,
Ma Hebo1ORCID,
Ma Yuling2ORCID,
Ren Zhaochun3ORCID,
Zhang Chen4ORCID,
Ko James5ORCID
Affiliation:
1. Shandong University of Finance and Economics, China
2. Shandong Jianzhu University, China
3. Leiden University, The Netherlands
4. Hong Kong Polytechnic University, China
5. Education University of Hong Kong, China
Abstract
Knowledge tracing aims to trace students’ evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this article, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students’ learning interactions to capture the heterogeneous exercise–concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To combine the dual graph models, we introduce the technique of online knowledge distillation. This choice arises from the observation that, while the knowledge tracing model is designed to predict students’ responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger ensemble teacher model, which provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.
Funder
National Natural Science Foundation of China
Shandong Provincial Natural Science Foundation Key Project
Shandong Provincial Natural Science Foundation
Taishan Scholar Program of Shandong Province
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Science Applications,General Business, Management and Accounting,Information Systems
Reference57 articles.
1. Knowledge Tracing with Sequential Key-Value Memory Networks
2. Rohan Anil Gabriel Pereyra Alexandre Passos Robert Ormandi George E Dahl and Geoffrey E Hinton. 2018. Large scale distributed neural network training through online distillation. In Proceedings of the 6th International Conference on Learning Representations.
3. Efficient neural matrix factorization without sampling for recommendation;Chen Chong;ACM Trans. Inf. Syst.,2020
4. Learning Elastic Embeddings for Customizing On-Device Recommenders
5. Neural feature-aware recommendation with signed hypergraph convolutional network;Chen Xu;ACM Trans. Inf. Syst.,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Graph-based Dynamic Interactive Knowledge Tracing;Proceedings of the 2023 8th International Conference on Distance Education and Learning;2023-06-09