ADSEL: Adaptive dual self-expression learning for EEG feature selection via incomplete multi-dimensional emotional tagging

2025-08-07

AI Summary

In EEG-based multidimensional emotion recognition, high-dimensional features often cause overfitting, limited sample sizes hinder generalization, and labels are frequently incomplete due to subjectivity and open-ended data collection—yet existing methods neglect inter-sample correlations within the label space and their interaction with feature dimensions. Method: We propose an adaptive dual-path self-expression learning framework that introduces, for the first time, a bidirectional (sample–dimension) self-expression mechanism. It jointly models inter-sample and inter-dimension correlations in the label space to enable cooperative feature selection and incomplete label recovery. The framework integrates adaptive dual self-expression with least-squares regression to enhance both dimensionality reduction efficiency and label imputation accuracy. Results: Extensive experiments on public benchmarks demonstrate significant improvements in classification accuracy and robustness over baseline methods—particularly under low signal-to-noise ratios and high label missing rates.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

EEG based multi-dimension emotion recognition has attracted substantial research interest in human computer interfaces. However, the high dimensionality of EEG features, coupled with limited sample sizes, frequently leads to classifier overfitting and high computational complexity. Feature selection constitutes a critical strategy for mitigating these challenges. Most existing EEG feature selection methods assume complete multi-dimensional emotion labels. In practice, open acquisition environment, and the inherent subjectivity of emotion perception often result in incomplete label data, which can compromise model generalization. Additionally, existing feature selection methods for handling incomplete multi-dimensional labels primarily focus on correlations among various dimensions during label recovery, neglecting the correlation between samples in the label space and their interaction with various dimensions. To address these issues, we propose a novel incomplete multi-dimensional feature selection algorithm for EEG-based emotion recognition. The proposed method integrates an adaptive dual self-expression learning (ADSEL) with least squares regression. ADSEL establishes a bidirectional pathway between sample-level and dimension-level self-expression learning processes within the label space. It could facilitate the cross-sharing of learned information between these processes, enabling the simultaneous exploitation of effective information across both samples and dimensions for label reconstruction. Consequently, ADSEL could enhances label recovery accuracy and effectively identifies the optimal EEG feature subset for multi-dimensional emotion recognition.

Problem

• High-dimensional EEG features cause overfitting and complexity
• Incomplete emotion labels reduce model generalization accuracy
• Existing methods neglect sample-dimension correlations in label space

Innovation

• Adaptive dual self-expression learning for EEG
• Bidirectional sample-dimension information sharing
• Simultaneous label recovery and feature selection