# Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective Source: [Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective]() Collection index: [llms.txt]() Data updated: 2026-01-10T05:00:05.200Z Authors: Ziwen Wang, Shangshang Yang, Xiaoshan Yu, Haiping Ma, Xingyi Zhang Published: 2026-01-08T13:17:40.000Z ## Abstract With the advancement of network technologies, intelligent tutoring systems (ITS) have emerged to deliver increasingly precise and tailored personalized learning services. Cognitive diagnosis (CD) has emerged as a core research task in ITS, aiming to infer learners' mastery of specific knowledge concepts by modeling the mapping between learning behavior data and knowledge states. However, existing research prioritizes model performance enhancement while neglecting the pervasive noise contamination in observed response data, significantly hindering practical deployment. Furthermore, current cognitive diagnosis models (CDMs) rely heavily on researchers' domain expertise for structural design, which fails to exhaustively explore architectural possibilities, thus leaving model architectures' full potential untapped. To address this issue, we propose OSCD, an evolutionary multi-objective One-Shot neural architecture search method for Cognitive Diagnosis, designed to efficiently and robustly improve the model's capability in assessing learner proficiency. Specifically, OSCD operates through two distinct stages: training and searching. During the training stage, we construct a search space encompassing diverse architectural combinations and train a weight-sharing supernet represented via the complete binary tree topology, enabling comprehensive exploration of potential architectures beyond manual design priors. In the searching stage, we formulate the optimal architecture search under heterogeneous noise scenarios as a multi-objective optimization problem (MOP), and develop an optimization framework integrating a Pareto-optimal solution search strategy with cross-scenario performance evaluation for resolution. Extensive experiments on real-world educational datasets validate the effectiveness and robustness of the optimal architectures discovered by our OSCD model for CD tasks. ## 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. - [Cognitive Diagnosis on ASSIST09 (60%/20%/20%)](): Cognitive Diagnosis; ASSIST09 (60%/20%/20%); Accuracy: 73.03. - [Cognitive Diagnosis on ASSIST09 (70%/10%/20%)](): Cognitive Diagnosis; ASSIST09 (70%/10%/20%); Accuracy: 73.41. - [Cognitive Diagnosis on SLP-Math (50%/20%/30%)](): Cognitive Diagnosis; SLP-Math (50%/20%/30%); ACC: 0.7868. - [Cognitive Diagnosis on SLP-Math (60% 20% 20%)](): Cognitive Diagnosis; SLP-Math (60% 20% 20%); ACC: 78.73. - [Cognitive Diagnosis on SLP-Math (80%/10%/10%)](): Cognitive Diagnosis; SLP-Math (80%/10%/10%); Accuracy: 79.06. - [Learner Performance Prediction on SLP-Math](): Learner Performance Prediction; SLP-Math; Log Miss (10%) AUC Change Ratio: -0.00139. - [Cognitive Diagnosis on ASSIST09 (50%/20%/30%)](): Cognitive Diagnosis; ASSIST09 (50%/20%/30%); ACC: 0.7242. - [Cognitive Diagnosis on ASSIST09 (80%/10%/10%)](): Cognitive Diagnosis; ASSIST09 (80%/10%/10%); Accuracy: 73.45. - [Cognitive Diagnosis on SLP-Math (70%/10%/20%)](): Cognitive Diagnosis; SLP-Math (70%/10%/20%); Acc: 79.29. - [Learner performance prediction on ASSIST09](): Learner Performance Prediction; ASSIST09; Time Cost: 26.1. - [Time Cost Measurement on SLP-Math (Learner performance prediction)](): Learner Performance Prediction; SLP-Math; Time Cost: 51.7. ## Original sources and implementation [Original paper]() [PDF]()