Justus Meyer zu Bexten

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 and within-subject motor-imagery classification under spatially informed channel reduction. Functional robustness is tested through the generalizability of linear probes across channel counts, while representational robustness is assessed through within-subject similarity and preservation of between-subject geometry. The four models show distinct robustness profiles, and the two axes dissociate: large changes in embedding similarity need not come with comparable probe degradation, and stable embeddings can still lose downstream performance. Comparing two readouts of the same encoder further shows that aggregation, not the encoder alone, determines functional robustness: pooling into anatomically aligned regions degrades less than a learned global readout, despite being montage-invariant by construction. Montage robustness is therefore a joint property of the encoder and its aggregation, and characterizing it requires both a representational and a functional axis. Input compatibility alone is evidence for neither.

@misc{steglich2026montage,
  title         = {Representational and Functional Robustness to Electrode Montages in EEG Foundation Models},
  author        = {Steglich, Jakob and Meyer zu Bexten, Justus and Moradi, Shakiba and Ciernik, Laure and Hofmann, Simon M. and Jamshidi Idaji, Mina},
  year          = {2026},
  eprint        = {2609.36288},
  archivePrefix = {arXiv},
  primaryClass  = {cs.LG},
  doi           = {10.48550/arXiv.2609.36288},
  url           = {https://arxiv.org/abs/2609.36288}
}

Emerging foundation models (FMs) in electroencephalography (EEG) promise a path to scale deep learning in diagnostics and brain-computer interfaces despite data scarcity, yet their opaque nature remains a barrier to wider adoption. We investigate attention-aware Layer-wise relevance propagation (LRP) as a post-hoc attribution method for EEG-FMs, extending LRP's use on convolutional neural network (CNN)-based EEG models to the Transformer architectures that current FMs are based on. We find that LRP can both verify EEG-FM decisions and surface novel, biologically plausible hypotheses from them. In motor imagery, it unmasks "Clever Hans" behavior where models prioritize task-correlated ocular signals over the intended motor correlates. In a naturalistic paradigm for affect prediction, it reveals a recurring reliance on a central electrode cluster, suggesting a candidate sensorimotor signature of arousal. Though heatmap interpretation remains ambiguous in this complex domain, the results position LRP as a tool for both verification and exploration of EEG-FMs, a role that will grow in both importance and discovery potential as the underlying models mature.

@misc{meyerzubexten2026cleverhans,
  title         = {From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP},
  author        = {Meyer zu Bexten, Justus and Scherf, Nico and Franczyk, Bogdan and Hofmann, Simon M.},
  year          = {2026},
  eprint        = {2605.11885},
  archivePrefix = {arXiv},
  doi           = {10.48550/arXiv.2605.11885},
  url           = {https://arxiv.org/abs/2605.11885}
}