PaperarXiv:2509.22050
BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models
NeurIPS 2026 (accepted, per arXiv v3 comment and repo README); arXiv 2509.22050 v1 2025-09-26 (earlier title 'BrainPro: Towards Large-scale Brain State-aware EEG Representation Learning'), v3 2026-10-21
Open codeOpen weights
TL;DR
Maps each dataset's electrode montage onto a universal channel-region template and retrieves channel- and region-level spatial filters (topographic retrieval), so the spatial basis is explicit and montage-independent. One shared encoder plus process-associated branches (affective, motor, auxiliary residual). Protocol-derived mental-process cues pick the active branch and weight the masked-reconstruction loss by scalp region. Pretraining: ~2,400 h EEG (≈2,180 h after cleaning), 10 s clips at 200 Hz, mask ratio 0.5, 30 epochs on 5× A800. 7.69 M parameters, 531 M FLOPs (vs EEGPT 51.66 M).
- Form factor: other
Abstract
EEG foundation models are pretrained on heterogeneous corpora, but two challenges remain underexplored: (1) experimental protocols provide mental-process cues that are rarely used in masked pretraining, and (2) electrode montages vary across datasets, making spatial representations montage-dependent. Existing methods typically learn a single general-purpose representation and model spatial structure implicitly, limiting their ability to exploit process-related information under montage heterogeneity. We introduce BrainPro, a process-conditioned self-supervised pretraining framework that couples topographic retrieval with shared and process-associated representation learning. BrainPro maps dataset-specific montages to a universal channel-region template and retrieves channel- and region-level spatial filters to form a topographically aligned spatial basis. Over this basis, BrainPro learns a shared encoder for general EEG structure and additional affective, motor-related, and auxiliary residual branches for process-associated variation. Protocol-derived mental-process cues condition branch activation and region-weighted masked reconstruction, incorporating topographic spatial priors and process information. Across nine public BCI benchmarks, BrainPro achieves strong performance among evaluated baselines. Ablations, channel-drop analysis, encoder-configuration studies, and spatial-filter visualizations suggest that topographic retrieval and process-conditioned representation learning jointly improve EEG decoding. Our code is available at https://github.com/yi-ding-cs/BrainPro.
Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
Models
How it works
Cite this paper
APA
Ding, Y., Jiang, M., Jiang, W., Zhang, S., Zhou, X., Liu, C., Li, S., Li, Y., & Guan, C. (2025). BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models. NeurIPS 2026. https://arxiv.org/abs/2509.22050
BibTeX
@inproceedings{ding2025brainpro,
title = {{BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models}},
author = {Ding, Yi and Jiang, Muyun and Jiang, Weibang and Zhang, Shuailei and Zhou, Xinliang and Liu, Chenyu and Li, Shanglin and Li, Yong and Guan, Cuntai},
year = {2025},
booktitle = {NeurIPS 2026},
eprint = {2509.22050},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
