Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· pp. 3576-3584· 0 citations· 47 references
TL;DR
FedGLoRA freezes the backbone and communicates only LoRA adapters via a dual-branch design, and aggregates global updates on a Grassmann subspace with a Grassmann-proximal constraint, and uses bidirectional distillation to mitigate imbalance.
Abstract
Large EEG Models (LEMs) are drawing increasing attention in EEG, as large-scale pretraining yields transferable representations that improve generalization. As EEG research moves to real-world deployment, objectives and paradigms diversify, yielding increasingly heterogeneous and unevenly scaled datasets across institutions. This evolution induces distribution drift and scale imbalance, making static pretrained LEMs brittle and requiring adaptation to newly collected data. Under the constraints of the high cost of retraining and the privacy sensitivity of newly collected data, federated learning offers a practical route to update LEMs via decentralized parameter updates. Yet standard federated fine-tuning is unstable for pretrained LEMs, suffering backbone drift, misaligned updates under non-IID heterogeneity, and scale imbalance. We propose FedGLoRA: we freeze the backbone and communicate only LoRA adapters via a dual-branch design, with a shared global branch and a private on-device branch. FedGLoRA aggregates global updates on a Grassmann subspace with a Grassmann-proximal constraint, and uses bidirectional distillation to mitigate imbalance. Experiments on motor imagery and emotion recognition show consistent gains and improved stability over strong baselines.
EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrained clinical settings due to high computational requirements. In this work, we i...
It is observed that personalised SPDNet reaches higher accuracy than both standard FL and centralised training, while converging in fewer rounds and communicating fewer parameters than standard FL.
Thibault Pautrel, Florent Bouchard, Ammar Mian et al.· 0 citations
Disentangled EFM Fine-Tuning (DEFT) is proposed, a plug-and-play adapter for EFM fine-tuning that improves matched fine-tuning baselines and encourages branch disentanglement of pretrained tokens into task-oriented content and subject-consistent style.
Yu-Qiu Deng, Muyun Jiang, Zong-Peng Zhang et al.· 0 citations
BRIDGE-EEG, an efficient multi-task EEG classification pipeline that preserves the benefits of pretraining while reducing model size is introduced and six benchmarks spanning abnormality detection, motor imagery, and emotion recognition are evaluated.
Meghna Roy Chowdhury, Cheng-Wei Zhou, Hao-Tian Yu et al.· 0 citations
Electroencephalography (EEG) based brain-computer interfaces enable direct brain-to-device communication for applications such as rehabilitation and communication. However, their practical utility is often limited as the non-stationary nature of the EEG data introduces distribution shifts across domains (e.g., sessions...
Shang-Lin Li, Shi-Wen Chu, Okan Koç et al.· 0 citations
Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a benchmark for online adaptation and compare two widely used pipeline families, Common Spatial Patterns (CSP) and Riemannian covariance-based methods, under time-ordered...
B. Kozyrskiy, Artem M. Grachev, Abraham Camelo-Guerrero· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.