Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective

2026-01-08

arXiv.org

AI Summary

This work proposes OSCD, a novel cognitive diagnosis method that addresses the limitations of existing models, which are often sensitive to observational noise and constrained by manually designed architectures, thereby struggling to balance robustness and performance. OSCD introduces one-shot neural architecture search into cognitive diagnosis for the first time, constructing a weight-sharing supernetwork based on a complete binary tree topology. Within a diverse search space encompassing numerous structural combinations, Pareto-optimal architectures are identified through evolutionary multi-objective optimization. By formulating architecture search as a multi-objective problem and incorporating cross-noise-scenario evaluation, OSCD overcomes the constraints of human-designed structures. Experiments on multiple real-world educational datasets demonstrate that the discovered architectures consistently outperform baseline methods across varying noise conditions, achieving both high accuracy and strong robustness.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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.

Problem

• Cognitive Diagnosis
• Robustness
• Noise Contamination
• Neural Architecture Search
• Model Architecture

Innovation

• neural architecture search
• cognitive diagnosis
• robustness
• multi-objective optimization
• one-shot NAS