English

Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability

Machine Learning 2026-05-11 v1 Artificial Intelligence Human-Computer Interaction Neural and Evolutionary Computing Signal Processing

Abstract

Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained and evaluated under a single, unreported preprocessing pipeline. We formalize preprocessing choices as a counterfactual intervention space and show that EEG predictions are surprisingly unstable under this space: across six datasets spanning four paradigms, up to 42% of trial-level predictions flip when only the preprocessing changes, a variability that standard uncertainty methods do not explicitly quantify because they condition on a fixed preprocessing pipeline. We provide three tools to make this instability measurable, decomposable, and reducible. First, a Walsh-Hadamard decomposition of the 2^7 pipeline space reveals that sensitivity is near-additive in practice under the binary intervention design, enabling efficient step-by-step optimization. Second, we introduce Preprocessing Uncertainty (PU), a per-trial diagnostic that captures a dimension of instability complementary to model-based confidence. Third, we study Normalized Adaptive PGI (NA-PGI), a graph-structured regularizer that exploits the compositional structure of preprocessing interventions as one mitigation strategy with clear scope conditions.

Keywords

Cite

@article{arxiv.2605.07212,
  title  = {Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability},
  author = {Dengzhe Hou and Zihao Wu and Lingyu Jiang and Zirui Li and Fangzhou Lin and Kazunori D. Yamada},
  journal= {arXiv preprint arXiv:2605.07212},
  year   = {2026}
}
R2 v1 2026-07-01T12:56:51.153Z