SAINT+: Integrating Temporal Features for EdNet Correctness Prediction

Abstract

We propose SAINT+, a successor of SAINT which is a Transformer based knowledge tracing model that separately processes exercise information and student response information. Following the architecture of SAINT, SAINT+ has an encoder-decoder structure where the encoder applies self-attention layers to a stream of exercise embeddings, and the decoder alternately applies self-attention layers and encoder-decoder attention layers to streams of response embeddings and encoder output. Moreover, SAINT+ incorporates two temporal feature embeddings into the response embeddings: elapsed time, the time taken for a student to answer, and lag time, the time interval between adjacent learning activities. We empirically evaluate the effectiveness of SAINT+ on EdNet, the largest publicly available benchmark dataset in the education domain. Experimental results show that SAINT+ achieves state-of-the-art performance in knowledge tracing with an improvement of 1.25% in area under receiver operating characteristic curve compared to SAINT, the current state-of-the-art model in EdNet dataset.

arXiv commentLAK 2021

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Deep Knowledge Tracing
• A Self-Attentive model for Knowledge Tracing
• Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess
• HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing

Cited by in corpus (12)

• A Survey of Knowledge Tracing: Models, Variants, and Applications
• Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs
• LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• AAKT: Enhancing Knowledge Tracing with Alternate Autoregressive Modeling
• Adaptation of the Multi-Concept Multivariate Elo Rating System to Medical Students Training Data
• LSTM-SAKT: LSTM-Encoded SAKT-like Transformer for Knowledge Tracing
• Last Query Transformer RNN for knowledge tracing
• MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing
• Prerequisite Structure Discovery in Intelligent Tutoring Systems
• Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction
• Riiid! Answer Correctness Prediction Kaggle Challenge: 4th Place Solution Summary