Forgetting-aware Linear Bias for Attentive Knowledge Tracing

TL;DR

This paper introduces FoLiBi, a linear bias mechanism that accounts for forgetting behavior in attention-based knowledge tracing models, improving their accuracy on benchmark datasets.

Contribution

It proposes a simple linear bias method, FoLiBi, to incorporate forgetting behavior into existing attentive KT models, enhancing their performance.

Findings

FoLiBi improves AUC by up to 2.58% on benchmarks.

Incorporating forgetting behavior enhances KT model accuracy.

FoLiBi is compatible with existing models and easy to implement.

Abstract

Knowledge Tracing (KT) aims to track proficiency based on a question-solving history, allowing us to offer a streamlined curriculum. Recent studies actively utilize attention-based mechanisms to capture the correlation between questions and combine it with the learner's characteristics for responses. However, our empirical study shows that existing attention-based KT models neglect the learner's forgetting behavior, especially as the interaction history becomes longer. This problem arises from the bias that overprioritizes the correlation of questions while inadvertently ignoring the impact of forgetting behavior. This paper proposes a simple-yet-effective solution, namely Forgetting-aware Linear Bias (FoLiBi), to reflect forgetting behavior as a linear bias. Despite its simplicity, FoLiBi is readily equipped with existing attentive KT models by effectively decomposing question correlations with forgetting behavior. FoLiBi plugged with several KT models yields a consistent improvement of up to 2.58% in AUC over state-of-the-art KT models on four benchmark datasets.