# A Novel Semi-supervised Meta Learning Method for Subject-transfer Brain-computer Interface

arXiv: https://arxiv.org/abs/2209.03785 · HTML: https://mlsanity.com/paper/2209.03785/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 60 references that are in the map.
- First posted on arXiv 7 Sep 2022.

## Builds on (most cited first, 15 of 15)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG](https://mlsanity.com/paper/1703.04046/) (2017)
- [EEG-Based Emotion Recognition Using Regularized Graph Neural Networks](https://mlsanity.com/paper/1907.07835/) (2019)
- [Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016](https://mlsanity.com/paper/2004.06286/) (2020)
- [Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification](https://mlsanity.com/paper/1805.06546/) (2018)
- [A Novel Bi-hemispheric Discrepancy Model for EEG Emotion Recognition](https://mlsanity.com/paper/1906.01704/) (2019)
- [PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition](https://mlsanity.com/paper/2202.05400/) (2022)
- [Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification](https://mlsanity.com/paper/2003.01300/) (2020)
- [CNN-based Approaches For Cross-Subject Classification in Motor Imagery: From The State-of-The-Art to DynamicNet](https://mlsanity.com/paper/2105.07917/) (2021)
- [Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classification](https://mlsanity.com/paper/2003.06113/) (2020)
- [Few-shot Decoding of Brain Activation Maps](https://mlsanity.com/paper/2010.12500/) (2020)
- [Diffuse to fuse EEG spectra -- intrinsic geometry of sleep dynamics for classification](https://mlsanity.com/paper/1803.01710/) (2018)
- [Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing](https://mlsanity.com/paper/2103.08664/) (2021)

## Built on by (most cited first, 6 of 6)

- [Evaluating the structure of cognitive tasks with transfer learning](https://mlsanity.com/paper/2308.02408/) (2023)
- [A Survey of Few-Shot Learning for Biomedical Time Series](https://mlsanity.com/paper/2405.02485/) (2024)
- [Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms](https://mlsanity.com/paper/2409.07989/) (2024)
- [Accurate deep learning sub-grid scale models for large eddy simulations](https://mlsanity.com/paper/2307.10060/) (2023)
- [Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface](https://mlsanity.com/paper/2404.15350/) (2024)
- [FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition](https://mlsanity.com/paper/2503.18998/) (2025)

## Abstract (arXiv)

Brain-computer interface (BCI) provides a direct communication pathway between human brain and external devices. Before a new subject could use BCI, a calibration procedure is usually required. Because the inter- and intra-subject variances are so large that the models trained by the existing subjects perform poorly on new subjects. Therefore, effective subject-transfer and calibration method is essential. In this paper, we propose a semi-supervised meta learning (SSML) method for subject-transfer learning in BCIs. The proposed SSML learns a meta model with the existing subjects first, then fine-tunes the model in a semi-supervised learning manner, i.e. using few labeled and many unlabeled samples of target subject for calibration. It is significant for BCI applications where the labeled data are scarce or expensive while unlabeled data are readily available. To verify the SSML method, three different BCI paradigms are tested: 1) event-related potential detection; 2) emotion recognition; and 3) sleep staging. The SSML achieved significant improvements of over 15% on the first two paradigms and 4.9% on the third. The experimental results demonstrated the effectiveness and potential of the SSML method in BCI applications.