LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
This addresses the challenge of building large-scale EEG models for researchers and clinicians by enabling efficient generalization across diverse electrode layouts, though it is incremental in improving existing foundation model approaches.
The paper tackles the problem of topological heterogeneity in EEG data by introducing LUNA, a self-supervised foundation model that compresses multi-channel EEG into a fixed-size, topology-agnostic latent space, achieving state-of-the-art results such as 0.921 AUROC on TUAR while reducing FLOPs by 300x and GPU memory use by up to 10x.
Electroencephalography (EEG) offers a non-invasive lens into human brain activity, but building large-scale models is hampered by topological heterogeneity: each public EEG data defines its own electrode layout, limiting generalization. We introduce LUNA (Latent Unified Network Architecture), a self-supervised foundation model that reconciles disparate electrode geometries while scaling linearly -- not quadratically -- with channel count. LUNA compresses multi-channel EEG into a fixed-size, topology-agnostic latent space via learned queries and cross-attention. Downstream transformer blocks then operate exclusively on this latent representation using patch-wise temporal self-attention, decoupling computation from electrode count. Pre-trained on TUEG and Siena (over 21,000 hours of raw EEG across diverse montages) using a masked-patch reconstruction objective, LUNA transfers effectively to four downstream tasks: abnormality detection, artifact rejection, slowing classification, and emotion recognition. It demonstrates highly competitive performance across several benchmarks, achieving state-of-the-art results on TUAR and TUSL, e.g., 0.921 AUROC on TUAR, while reducing FLOPs by 300x and trimming GPU memory use by up to 10x. Critically, these gains are consistent across all evaluated electrode configurations. Code is available at https://github.com/pulp-bio/BioFoundation