mlsanityData to 7 Oct 2026

Mitigating Subject Dependency in EEG Decoding with Subject-Specific Low-Rank Adapters

arXiv 2510.08059 ↗First posted 9 Oct 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Subject-specific distribution shifts represent a fundamental obstacle to developing foundation models for brain decoding. We propose the Subject-Specific Low-Rank Adapter (SuLoRA), a drop-in replacement for standard linear or convolutional layers that captures inter-subject variability by decomposing weights into a shared, subject-invariant component and a lightweight, low-rank correction unique to each subject. This explicit separation enables existing architectures to become robust to subject shifts without architectural redesign. We evaluate SuLoRA on MEG speech perception and EEG motor imagery tasks across CNN and transformer architectures. In the speech decoding task, SuLoRA exceeds the baseline performance with half of the parameters. On motor imagery dataset, SuLoRA outperforms both subject-agnostic models and independently trained subject-specific models. SuLoRA offers a practical path towards effective cross-subject foundation models for brain signal applications.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 61 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

28 of 61 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  8. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  9. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  10. 2024Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCIcited by 311
  11. 2021BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG datacited by 194
  12. 2022Decoding speech perception from non-invasive brain recordingscited by 129
16 more
  1. 2022Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equationscited by 42
  2. 2024The largest EEG-based BCI reproducibility study for open science: the MOABB benchmarkcited by 28
  3. 2025Scaling laws for decoding images from brain activitycited by 21
  4. 2025Brain-to-Text Decoding: A Non-invasive Approach via Typingcited by 21
  5. 2024EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task Classificationcited by 18
  6. 2022Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeXcited by 17
  7. 2020An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computingcited by 15
  8. 2025Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuningcited by 15
  9. 2024Decoding individual words from non-invasive brain recordings across 723 participantscited by 13
  10. 2023Geometry-aware training of factorized layers in tensor Tucker formatcited by 12
  11. 2025EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decodingcited by 12
  12. 2024Federated Dynamical Low-Rank Training with Global Loss Convergence Guaranteescited by 7
  13. 2025Is Limited Participant Diversity Impeding EEG-based Machine Learning?cited by 6
  14. 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attackscited by 5
  15. 2025A geometric framework for momentum-based optimizers for low-rank trainingcited by 5
  16. 2024Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendationscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026The Identity Trap in EEG Foundation Models: A Diagnostic Auditcited by 1
  2. 2026Learning aligned EEG representations with subject-specific encoderscited by 0
  3. 2026Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Modelcited by 0
  4. 2026Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decodingcited by 0