Consistency and Monotonicity Regularization for Neural Knowledge Tracing
This work addresses the challenge of enhancing model generalization in online learning and AI in Education, though it is incremental as it builds on existing neural network methods.
The paper tackled the problem of improving generalization in Knowledge Tracing models by proposing three novel data augmentation techniques and corresponding regularization losses that enforce consistency and monotonicity biases. The result was consistent performance improvements across benchmarks, such as a 6.3% AUC increase under the DKT model on the ASSISTmentsChall dataset.
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 biases on the model's predictions for the original and augmented sequence. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances, under 3 widely-used neural networks and 4 public benchmarks, e.g., it yields 6.3% improvement in AUC under the DKT model and the ASSISTmentsChall dataset.