Mamba4KT: An Efficient and Effective Mamba-based Knowledge Tracing Model

This paper introduces Mamba4KT, a knowledge tracing model that predicts student performance based on past interactions while improving training/inference efficiency and resource utilization compared to attention-based models. The model aims to balance prediction accuracy with computational efficiency in adaptive learning systems.

Knowledge tracing (KT) enhances student learning by leveraging past performance to predict future performance. Current research utilizes models based on attention mechanisms and recurrent neural network structures to capture long-term dependencies and correlations between exercises, aiming to improve model accuracy. Due to the growing amount of data in smart education scenarios, this poses a challenge in terms of time and space consumption for knowledge tracing models. However, existing research

Source

Framework Categories

Tool Types

Tags