Probing EEG Foundation Model Attention Maps for Lightweight Interpretable Emotion Recognition
Auteurs : L. N. Arvanitopoulos, A. Dragomir, C. A. Fidas, A. Bezerianos
Résumé scientifique
Foundation Models (FMs) trained on EEG signals promise subject- and dataset-independent pipelines for brain-computer interface (BCI) applications, but have yet to consistently outperform task-specific architectures, and their large representations are costly to compute and store. As a means of advancing the understanding of the Foundation Models' inner mechanisms, we propose a lightweight alternative that exploits the self-attention mechanism of REVE, a pretrained EEG FM, to derive features similar to weighted Functional Connectivity (FC) without any fine-tuning. Inspired by kernel-based FC matrices, we aggregate the raw first-layer attention weights of a single head over the full duration of dataset trials into weighted channel-to-channel adjacency matrices. These matrices replace standard encoder representation vectors as classification features, substantially reducing computational cost. We further introduce a label-free, symmetry-based criterion, motivated by the emergence of near-symmetric attention patterns in trained encoder-decoder transformers, ranking attention heads by how much discriminative information they carry. Classical machine learning classifiers are then trained on the single most informative head's attention-derived FC matrix and achieve balanced accuracy and F1 scores on the SEED-IV emotion-recognition dataset that are competitive with several fully fine-tuned state-of-the-art EEG Foundation Models, requiring at least two orders of magnitude fewer calculations than the standard use of the encoder. Subsequent cortical region analysis revealed a significant over-representation of frontal region connections by ranking the most discriminative FC matrix connectivity edges, validating our methods as consistent with prior affective-computing literature. These results suggest that interpretable, computationally inexpensive linear probing of attention maps is a viable route to deploying EEG Foundation Models in resource-constrained settings.
Les articles autour de lui, par date et par proximité
Plus haut, c’est plus proche de cet article ; à gauche, c’est plus ancien. Les traits relient les articles proches entre eux : les groupes de traits sont des sous-thèmes. Sélectionnez un point pour voir pourquoi il est là. Retour au résumé de cet article
Les articles autour de celui-ci
Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.
Les articles les plus proches
-
Foundation Models for Neural Signal Decoding: EEG‐Centered Perspectives Toward Unified RepresentationsJii Kwon, You-Min Shin · 2025 · European Journal of Neuroscience · cité 5 fois · Pas encore résumé
Résumé scientifique
Neural signals such as EEG, ECoG, and intracortical recordings offer a valuable window into brain dynamics but remain difficult to decode due to high dimensionality, nonstationarity, and substantial interindividual variability. Traditional machine learning and deep learning models often show limited generalizability and insufficient interpretability in these settings. Foundation models (FMs)—large‐scale architectures pretrained on diverse datasets—have recently emerged as a promising paradigm for building robust, transferable, and physiologically grounded neural representations. Among these modalities, EEG currently serves as the most practical and representative platform for FM development …
-
Representational and Functional Robustness to Electrode Montages in EEG Foundation ModelsJ. Steglich, Justus Meyer zu Bexten, Shakiba Moradi et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé
Résumé scientifique
EEG foundation models (EEG-FMs) are intended to generalize across different datasets by learning representations that, ideally, are invariant to dataset-specific EEG configurations such as electrode montages. However, EEG-FMs that accept different montages as input do not guarantee that representations and predictions remain stable across different electrode configurations, especially outside the training setting. In this work, we investigate the effects of different electrode montages through a joint functional and representational analysis of four EEG foundation models selected to span distinct montage-handling designs. We evaluate embeddings on cross-subject resting-state eyes-open/closed…
-
REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 SubjectsY. El Ouahidi, Jonathan Lys, Philipp Thölke et al. · 2025 · Neural Information Processing Systems · cité 150 fois · Pas encore résumé
Résumé scientifique
Foundation models have transformed AI by reducing reliance on task-specific data through large-scale pretraining. While successful in language and vision, their adoption in EEG has lagged due to the heterogeneity of public datasets, which are collected under varying protocols, devices, and electrode configurations. Existing EEG foundation models struggle to generalize across these variations, often restricting pretraining to a single setup, resulting in suboptimal performance, in particular under linear probing. We present REVE (Representation for EEG with Versatile Embeddings), a pretrained model explicitly designed to generalize across diverse EEG signals. REVE introduces a novel 4D positi…
-
A Survey on Attention-Based Deep Learning Methods for EEG Emotion RecognitionZhi-Xuan Qi · 2026 · Applied and Computational Engineering · Pas encore résumé
Résumé scientifique
Electroencephalography (EEG)-based emotion recognition has attracted increasing attention in recent years because of its potential applications in brain-computer interfaces, intelligent healthcare, and affective computing. With the rapid development of deep learning, attention mechanisms have gradually become an important component of EEG emotion recognition models, since they are able to improve feature representation by focusing on more informative EEG signals. This paper reviews recent attention-based deep learning methods for EEG emotion recognition, with particular attention to channel attention, temporal attention, and self-attention implemented in Transformer-based architectures. Thei…
-
Multi-Scale Attention-Enhanced BiLSTM Network for EEG Emotion RecognitionYong-Bin Zhang, Run-Yi Li, Xiu-Li Fu et al. · 2026 · IEEE Access · Pas encore résumé
Résumé scientifique
Over the last decade, significant progress has been made in detecting human emotions via electroencephalographic (EEG) recordings. Nevertheless, contemporary EEG-driven affect recognition techniques continue to encounter multiple hurdles, including insufficient feature extraction capability, inadequate modeling of local patterns, low feature extraction efficiency, high model complexity, and difficulty in practical deployment. To address these issues, we introduce an EEG-specific lightweight architecture for affective computing titled multi-scale Bidirectional Long Short-Term Memory with Attention (MS-BiLSTM-Attention). This model uses DE features, which are embedded into the EEG electrode to…
-
Multi-scale feature fusion and neural architecture search for electroencephalography-based affective-state recognition in public benchmark datasetsChi-Xun Guan, Yun-Han Wang · 2026 · Frontiers in Medicine · Pas encore résumé
Résumé scientifique
Electroencephalography (EEG)-based affective-state recognition may provide an objective neurophysiological complement to self-report scales and behavioral observations, but robust modeling remains difficult because EEG signals are non-stationary, temporally heterogeneous, and strongly subject-dependent. This study evaluated MFANet, a multi-scale feature fusion and neural architecture search-enhanced framework for binary classification of valence, arousal, and dominance. MFANet combines parallel one-dimensional convolutional branches with different receptive fields, channel-wise attention for adaptive feature recalibration, and a neural architecture search-guided long short-term memory module…
-
Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder TransferRita Huan-Ting Peng, Nhat Bui · 2026 · Pas encore résumé
Résumé scientifique
Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters and substantial computational resources. In this paper, we present the Universal Semantic EEG Foundation Model (USE-FM), a lightweight EEG foundation model that learns transferable neural representations through self-supervised signal reconstruction on the Temple University Hospital EEG Corpus (TUEG). After pretraining, the encoder is frozen and evaluated on two clinically distinct downstream tasks, abnormal EEG detection (TUAB) and epileptic seizure recognition (TUEP), using a unified frozen-transfer protocol against recent EEG foundation mode…
-
CoMET: A Contrastive-Masked Brain Foundation Model for Universal EEG RepresentationAng Li, Zikai Wang, Liu-Yin Yang et al. · 2025 · cité 8 fois · Pas encore résumé
Résumé scientifique
Electroencephalography (EEG) is a non-invasive technique for recording brain activity, widely used in brain-computer interfaces, clinic, and healthcare. Traditional EEG deep models typically focus on specific dataset and task, limiting model size and generalization. Recently, self-supervised brain foundation models have emerged and been applied to various downstream tasks. Nevertheless, these models still have limitations: current SOTA models typically rely on masked reconstruction strategy; however, EEG features of adjacent channels are highly correlated, which causes the pre-training to overly focus on low-dimensional signal-similarity features in local regions and neglect the global discr…
Les travaux antérieurs sur lesquels il s’appuie
-
AdaBrain-Bench: Benchmarking Brain Foundation Models for Brain-Computer Interface ApplicationsJia-Min Wu, Zichen Ren, Jun-Yu Wang et al. · 2025 · arXiv.org · preprint, non relu par les pairs · cité 22 fois · Pas encore résumé
Résumé scientifique
Non-invasive Brain-Computer Interfaces (BCI) offer a safe and accessible means of connecting the human brain to external devices, with broad applications in home and clinical settings to enhance human capabilities. However, the high noise level and limited task-specific data in non-invasive signals constrain decoding capabilities. Recently, the adoption of self-supervised pre-training is transforming the landscape of non-invasive BCI research, enabling the development of brain foundation models to capture generic neural representations from large-scale unlabeled electroencephalography (EEG) signals with substantial noises. However, despite these advances, the field currently lacks comprehens…
-
Systematic review of self-supervised foundation models for brain network representation using electroencephalographyHannah Portmann, Y. Morishima · 2026 · cité 1 fois · Pas encore résumé
Résumé scientifique
Automated analysis of electroencephalography (EEG) has recently undergone a paradigm shift. The introduction of transformer architectures and self-supervised pretraining (SSL) has led to the development of EEG foundation models. These models are pretrained on large amounts of unlabeled data and can be adapted to a range of downstream tasks. This systematic review summarizes recent SSL-trained EEG foundation models that learn whole-brain representations from multichannel EEG rather than representations derived from a single channel. We searched PubMed, IEEE Xplore, Scopus, and arXiv through July 21, 2025. Nineteen preprints and peer-reviewed articles met inclusion criteria. We extracted infor…
-
CBraMod: A Criss-Cross Brain Foundation Model for EEG DecodingJiquan Wang, Sha Zhao, Zhiling Luo et al. · 2024 · International Conference on Learning Representations · cité 322 fois · Pas encore résumé
Résumé scientifique
Electroencephalography (EEG) is a non-invasive technique to measure and record brain electrical activity, widely used in various BCI and healthcare applications. Early EEG decoding methods rely on supervised learning, limited by specific tasks and datasets, hindering model performance and generalizability. With the success of large language models, there is a growing body of studies focusing on EEG foundation models. However, these studies still leave challenges: Firstly, most of existing EEG foundation models employ full EEG modeling strategy. It models the spatial and temporal dependencies between all EEG patches together, but ignores that the spatial and temporal dependencies are heteroge…
-
CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG DecodingYuchen Zhou, Jia-Min Wu, Zichen Ren et al. · 2025 · Neural Information Processing Systems · cité 87 fois · Pas encore résumé
Résumé scientifique
Understanding and decoding brain activity from electroencephalography (EEG) signals is a fundamental challenge in neuroscience and AI, with applications in cognition, emotion recognition, diagnosis, and brain-computer interfaces. While recent EEG foundation models advance generalized decoding via unified architectures and large-scale pretraining, they adopt a scale-agnostic dense modeling paradigm inherited from NLP and vision. This design neglects a core property of neural activity: cross-scale spatiotemporal structure. EEG task patterns span a wide range of temporal and spatial scales, from short bursts to slow rhythms, and from localized cortical responses to distributed interactions. Ign…
-
EmotionMeter: A Multimodal Framework for Recognizing Human EmotionsWei-Long Zheng, Wei Liu, Yifei Lu et al. · 2019 · IEEE Transactions on Cybernetics · cité 1 233 fois · Pas encore résumé
Résumé scientifique
In this paper, we present a multimodal emotion recognition framework called EmotionMeter that combines brain waves and eye movements. To increase the feasibility and wearability of EmotionMeter in real-world applications, we design a six-electrode placement above the ears to collect electroencephalography (EEG) signals. We combine EEG and eye movements for integrating the internal cognitive states and external subconscious behaviors of users to improve the recognition accuracy of EmotionMeter. The experimental results demonstrate that modality fusion with multimodal deep neural networks can significantly enhance the performance compared with a single modality, and the best mean accuracy of 8…
Aller plus loin
Comment ces articles sont-ils trouvés ?
Nous comparons le titre et le résumé de cet article avec ceux de tous les articles résumés sur ce site, et avec les articles que Semantic Scholar recommande, ceux qu’il cite et ceux qui le citent (pour un article très cité, ses citations les plus récentes et, depuis OpenAlex, les plus citées). Parmi les travaux antérieurs et les suites, les articles qui s’utilisent en profondeur, une méthode qu’il utilise et les suites très citées remontent un peu. Les niveaux (très proche, proche, apparenté) viennent de la similarité des textes, pas d’un jugement de qualité ; * signale un article sans résumé, comparé par son titre. La phrase sous un article est écrite par une IA à partir des deux résumés : vérifiez-la dans les articles. Un article jugé hors sujet par trois lecteurs quitte la liste.
Mis à jour le 20 novembre 2026.