simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
Zitao Liu, Qiongqiong Liu, Jiahao Chen, Shuyan Huang, Weiqi Luo

TL;DR
simpleKT is a straightforward yet highly effective baseline for knowledge tracing that models question-specific variations and uses simple attention mechanisms, outperforming many complex deep learning models across multiple datasets.
Contribution
The paper introduces simpleKT, a new baseline for knowledge tracing that combines psychometric-inspired question modeling with basic attention, providing a strong, simple alternative to complex methods.
Findings
Achieves top 3 AUC ranking on multiple datasets
Wins 57, ties 3, and loses 16 against 12 DLKT methods
Outperforms many complex models with a simple approach
Abstract
Knowledge tracing (KT) is the problem of predicting students' future performance based on their historical interactions with intelligent tutoring systems. Recently, many works present lots of special methods for applying deep neural networks to KT from different perspectives like model architecture, adversarial augmentation and etc., which make the overall algorithm and system become more and more complex. Furthermore, due to the lack of standardized evaluation protocol \citep{liu2022pykt}, there is no widely agreed KT baselines and published experimental comparisons become inconsistent and self-contradictory, i.e., the reported AUC scores of DKT on ASSISTments2009 range from 0.721 to 0.821 \citep{minn2018deep,yeung2018addressing}. Therefore, in this paper, we provide a strong but simple baseline method to deal with the KT task named \textsc{simpleKT}. Inspired by the Rasch model in…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsIntelligent Tutoring Systems and Adaptive Learning · Online Learning and Analytics
