# Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing Source: [Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:38:21.966Z Authors: Shangshang Yang, Xiaoshan Yu, Ye Tian, Xueming Yan, Haiping Ma, Xingyi Zhang Published: 2023-10-02T13:19:33.000Z ## Abstract Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises. Despite the excellent performance of existing Transformer-based KT approaches, they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Knowledge Tracing on EdNet (test)](): Knowledge Tracing; EdNet (test); AUC: 0.8059. - [Knowledge Tracing on EdNet (60% train 30% test)](): Knowledge Tracing; EdNet (60% train 30% test); RMSE: 0.4215. - [Knowledge Tracing on RAIEd 2020 (60% train 30% test)](): Knowledge Tracing; RAIEd 2020 (60% train 30% test); RMSE: 0.4207. - [Knowledge Tracing on EdNet (50% train / 40% test)](): Knowledge Tracing; EdNet (50% train / 40% test); RMSE: 0.4219. - [Knowledge Tracing on RAIEd 2020 (50% train 40% test)](): Knowledge Tracing; RAIEd 2020 (50% train 40% test); RMSE: 0.42. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()