Last Query Transformer RNN for knowledge tracing
This work addresses knowledge tracing for educational applications, representing an incremental improvement in efficiency for sequence modeling.
The paper tackles the problem of predicting student answer correctness from past learning activities by introducing a model that combines transformer encoder and RNN, achieving first place in a Kaggle competition.
This paper presents an efficient model to predict a student's answer correctness given his past learning activities. Basically, I use both transformer encoder and RNN to deal with time series input. The novel point of the model is that it only uses the last input as query in transformer encoder, instead of all sequence, which makes QK matrix multiplication in transformer Encoder to have O(L) time complexity, instead of O(L^2). It allows the model to input longer sequence. Using this model I achieved the 1st place in the 'Riiid! Answer Correctness Prediction' competition hosted on kaggle.