Representational and Functional Robustness to Electrode Montages in EEG Foundation Models

2026-09-28

AI Summary

This study addresses the lack of robustness guarantees in existing EEG foundation models under varying electrode lead configurations. By jointly analyzing the representational and functional robustness of four models through techniques including spatial information channel reduction, linear probing, and geometric analysis of embedding similarities, this work investigates the impact of diverse lead setups and the role of aggregation mechanisms. The findings reveal a decoupling between representational and functional robustness, demonstrating that aggregation strategies, rather than encoders alone, determine downstream performance stability. Furthermore, this research establishes that input compatibility does not equate to robustness, and shows that anatomically aligned regional pooling yields greater functional resilience compared to global readout approaches.

Abstract

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.

Problem

• EEG foundation models
• electrode montages
• representational robustness
• functional robustness
• generalization

Innovation

• EEG Foundation Models
• Electrode Montage Robustness
• Representational Analysis
• Functional Robustness
• Aggregation Strategy