FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition

TL;DR

FACE addresses cross-subject EEG emotion recognition under limited labeled data by marrying a cross-view fusion module with a few-shot adapter guided by meta-learning. The CVF module fuses global brain connectivity and local spatial patterns in a subject-specific, meta-learned manner, while the FSA module enables rapid, subject-specific calibration through BN-augmented adapters and a MAML-style optimization. Across SEED, SEED-IV, and SEED-V, FACE achieves state-of-the-art or competitive performance in few-shot settings, demonstrating strong generalization with as few as a handful of labeled samples per class. The approach offers a practical solution for real-world cross-subject BCI scenarios where labeled target data are scarce, and it highlights the value of subject-specific fusion and adaptation in EEG emotion recognition.

Abstract

Cross-subject EEG emotion recognition is challenged by significant inter-subject variability and intricately entangled intra-subject variability. Existing works have primarily addressed these challenges through domain adaptation or generalization strategies. However, they typically require extensive target subject data or demonstrate limited generalization performance to unseen subjects. Recent few-shot learning paradigms attempt to address these limitations but often encounter catastrophic overfitting during subject-specific adaptation with limited samples. This article introduces the few-shot adapter with a cross-view fusion method called FACE for cross-subject EEG emotion recognition, which leverages dynamic multi-view fusion and effective subject-specific adaptation. Specifically, FACE incorporates a cross-view fusion module that dynamically integrates global brain connectivity with localized patterns via subject-specific fusion weights to provide complementary emotional information. Moreover, the few-shot adapter module is proposed to enable rapid adaptation for unseen subjects while reducing overfitting by enhancing adapter structures with meta-learning. Experimental results on three public EEG emotion recognition benchmarks demonstrate FACE's superior generalization performance over state-of-the-art methods. FACE provides a practical solution for cross-subject scenarios with limited labeled data.

Figures (6)

• Figure 1: Comparison of training data and processes between Few-Shot Learning (FSL) and traditional deep learning (DL) in cross-subject EEG emotion recognition. Traditional DL primarily relies on additional unlabeled target data for training, whereas FSL learns a subject-agnostic model in the source domain and fine-tunes it using only a few target-domain samples with few steps. DA denotes Domain Adaptation, DG denotes Domain Generalization, and SSL denotes Semi-Supervised Learning.
• Figure 2: Overview of the proposed FACE architecture in testing stage. For each unseen subject, a few labeled EEG signals are collected for rapid partial updates. Their EEG signals undergo spatial projection to construct spatial representations, which are then fed into FACE. The framework contains two core components: 1) The Cross-View Module fuses multi-view features to obtain unified representations, and 2) The Few-Shot Adapter Module adjusts the features to ensure subject-specific emotional clues is captured.
• Figure 3: Statistical comparison of different components on the (a) SEED, (b) SEED-IV, and (c) SEED-V dataset.
• Figure 4: t-SNE visualization of the SEED and SEED-IV datasets with and without the CVF module under the 5-shot setting. (a) Baseline w/o CVF module on SEED, (b) Baseline w/ CVF module on SEED, (c) Baseline w/o CVF module on SEED-IV, and (d) Baseline w/ CVF module on SEED-IV. Markers represent the ground truth labels, while colors indicate the predicted labels.
• Figure 5: Brain topographic maps illustrating the effects of 5-shot adaptation on (a) the SEED and (b) the SEED-IV dataset. The first row depicts the state before adaptation, while the second row represents the state after adaptation.