Consistency and Monotonicity Regularization for Neural Knowledge Tracing

Seewoo Lee, Youngduck Choi, Juneyoung Park, Byungsoo Kim, Jinwoo Shin

Keywords: knowledge tracing, data augmentation, regularization

Abstract: Knowledge Tracing (KT), tracking a human's knowledge acquisition, is a central component in online learning and AI in Education. In this paper, we present a simple, yet effective strategy to improve the generalization ability of KT models: we propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses that impose certain consistency or monotonicity bias on model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme significantly improve the prediction performances, under 3 widely-used neural networks and 4 public benchmarks for KT, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.

One-sentence Summary: We propose simple yet effective data augmentation strategies along with corresponding regularization losses for training knowledge tracing models.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=tuwdoyGQq