# EEG Decoding

3 related articles

Subscribe to updates

arXiv Nov 12, 2026
Cross-subject brain-image retrieval breaks on new people: SA-LBC anchors calibration to same-stimulus source responses, lifting MRR from 0.1867 to 0.2336
In cross-subject neural-image retrieval, comparing the mean of a few target observations with the global source mean conflates subject-specific representation shifts with differences in which stimuli were sampled. SA-LBC instead estimates a first-order shift by averaging residuals against same-stimulus source-population anchors, then shrinks the correction using source-derived uncertainty. On THINGS-EEG2 with 10 subjects under leave-one-subject-out evaluation, the Attention-CLIP ViT-B/32 configuration rises from 0.1867 MRR without calibration to 0.2013 and 0.2336, though retrieval gains remain representation-dependent.
In cross-subject neural-image retrieval, comparing the mean of a few target observations with the global source mean conflates subject-specific representation shifts with differences in which stimuli were sampled. SA-LBC instead estimates a first-order shift by averaging residuals against same-stimulus source-population anchors, then shrinks the correction using source-derived uncertainty. On THINGS-EEG2 with 10 subjects under leave-one-subject-out evaluation, the Attention-CLIP ViT-B/32 configuration rises from 0.1867 MRR without calibration to 0.2013 and 0.2336, though retrieval gains remain representation-dependent.
Xizhang Yao（First author）
Stimulus-Anchored Latent Bias Calibration Neural-Image Retrieval EEG Decoding Electroencephalography
bioRxiv Nov 10, 2026
EEG decoders stop depending on the cap: hTSMNet aligns any montage from electrode coordinates alone and leads every dataset after brief calibration
Electrode caps differ in channel count and layout across laboratories, so recordings do not even share an observation space, and cross-dataset EEG decoding has stayed limited. hTSMNet places a linear map generated from electrode coordinates in front of the decoding backbone, projecting any montage onto 15 fixed scalp anchors; the map has no subject-specific parameters, so unseen subjects and datasets align zero-shot. On a leave-one-dataset-out motor-imagery benchmark of three datasets and 172 subjects it matches the strongest comparator at strict zero-shot and reaches the highest accuracy on every dataset once a few calibration trials refit only the final classifier.
Electrode caps differ in channel count and layout across laboratories, so recordings do not even share an observation space, and cross-dataset EEG decoding has stayed limited. hTSMNet places a linear map generated from electrode coordinates in front of the decoding backbone, projecting any montage onto 15 fixed scalp anchors; the map has no subject-specific parameters, so unseen subjects and datasets align zero-shot. On a leave-one-dataset-out motor-imagery benchmark of three datasets and 172 subjects it matches the strongest comparator at strict zero-shot and reaches the highest accuracy on every dataset once a few calibration trials refit only the final classifier.
Advanced Telecommunications Research Institute International RIKEN Center for Advanced Intelligence Project Berlin Institute for the Foundations of Learning and Data
Huu Hoang（First author, Corresponding author）
hTSMNet Geometry-Conditioned Hyperalignment Cross-Dataset Transfer EEG Decoding Riemannian SPD-Manifold Decoding
arXiv Sep 26, 2026
Personalised federated learning lets SPDNet EEG decoding beat standard federated and centralised training on three motor-imagery datasets and outperform every EEGNet configuration on two of them
The work adapts personalised federated learning, in which all subjects share a trunk while each subject keeps its own head, to the Riemannian SPDNet, and compares it against standard federated learning and centralised training with the Euclidean EEGNet as a baseline; across three motor-imagery datasets spanning diverse channel, subject and class regimes, personalised SPDNet reaches higher accuracy than both standard federated and centralised training, converges in fewer rounds and communicates fewer parameters than standard federated learning, and outperforms every EEGNet configuration on two of the three datasets, although centralised EEGNet outperforms centralised SPDNet.
The work adapts personalised federated learning, in which all subjects share a trunk while each subject keeps its own head, to the Riemannian SPDNet, and compares it against standard federated learning and centralised training with the Euclidean EEGNet as a baseline; across three motor-imagery datasets spanning diverse channel, subject and class regimes, personalised SPDNet reaches higher accuracy than both standard federated and centralised training, converges in fewer rounds and communicates fewer parameters than standard federated learning, and outperforms every EEGNet configuration on two of the three datasets, although centralised EEGNet outperforms centralised SPDNet.
Centre National de la Recherche Scientifique Université Paris-Saclay Université Savoie Mont Blanc
Thibault Pautrel（First author）
Personalised Federated Learning Riemannian SPDNet EEGNet EEG Decoding

You’re all caught up

Cross-subject brain-image retrieval breaks on new people: SA-LBC anchors calibration to same-stimulus source responses, lifting MRR from 0.1867 to 0.2336

EEG decoders stop depending on the cap: hTSMNet aligns any montage from electrode coordinates alone and leads every dataset after brief calibration

Personalised federated learning lets SPDNet EEG decoding beat standard federated and centralised training on three motor-imagery datasets and outperform every EEGNet configuration on two of them