SSAS: Cross-subject EEG-based Emotion Recognition through Source Selection with Adversarial Strategy

2025-12-15

AI Summary

To address negative transfer caused by inter-subject variability in cross-subject EEG-based emotion recognition, this paper proposes a synergistic framework integrating source domain selection and adversarial learning. We introduce a novel Source Selection (SS) network that inversely models the domain adaptation process to identify high-quality source domains. A two-stage adversarial mechanism is designed, wherein a pre-trained domain discriminator guides adversarial training—intentionally perturbing class separability while amplifying inter-domain discrepancies—to encourage learning of emotion-discriminative and domain-invariant representations. Furthermore, differentiable domain label inversion and adaptive weighted loss are incorporated to theoretically ensure joint optimization of domain invariance and emotion discriminability. Our method achieves average accuracy improvements of 3.2–5.7% over state-of-the-art approaches on the SEED and SEED-IV benchmarks. The source code is publicly available.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Electroencephalographic (EEG) signals have long been applied in the field of affective brain-computer interfaces (aBCIs). Cross-subject EEG-based emotion recognition has demonstrated significant potential in practical applications due to its suitability across diverse people. However, most studies on cross-subject EEG-based emotion recognition neglect the presence of inter-individual variability and negative transfer phenomena during model training. To address this issue, a cross-subject EEG-based emotion recognition through source selection with adversarial strategy is introduced in this paper. The proposed method comprises two modules: the source selection network (SS) and the adversarial strategies network (AS). The SS uses domain labels to reverse-engineer the training process of domain adaptation. Its key idea is to disrupt class separability and magnify inter-domain differences, thereby raising the classification difficulty and forcing the model to learn domain-invariant yet emotion-relevant representations. The AS gets the source domain selection results and the pretrained domain discriminators from SS. The pretrained domain discriminators compute a novel loss aimed at enhancing the performance of domain classification during adversarial training, ensuring the balance of adversarial strategies. This paper provides theoretical insights into the proposed method and achieves outstanding performance on two EEG-based emotion datasets, SEED and SEED-IV. The code can be found at https://github.com/liuyici/SSAS.

Problem

• Addresses cross-subject EEG emotion recognition challenges
• Mitigates inter-individual variability and negative transfer issues
• Develops adversarial source selection for domain-invariant representations

Innovation

• Source selection network disrupts class separability for domain-invariant learning
• Adversarial strategies network enhances domain classification with novel loss
• Balances inter-domain differences to reduce negative transfer in cross-subject EEG