# Inter-subject Deep Transfer Learning for Motor Imagery EEG Decoding

arXiv: https://arxiv.org/abs/2103.05351 · HTML: https://mlsanity.com/paper/2103.05351/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 9 Mar 2021.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Transfer Learning in Brain-Computer Interfaces](https://mlsanity.com/paper/1512.00296/) (2015)
- [Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI](https://mlsanity.com/paper/1807.11752/) (2018)
- [Deep Transfer Learning for EEG-based Brain Computer Interface](https://mlsanity.com/paper/1808.01752/) (2018)

## Built on by (most cited first, 12 of 12)

- [2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets](https://mlsanity.com/paper/2202.12950/) (2022)
- [fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding](https://mlsanity.com/paper/2311.00342/) (2023)
- [A Systematic Evaluation of Euclidean Alignment with Deep Learning for EEG Decoding](https://mlsanity.com/paper/2401.10746/) (2024)
- [Team Cogitat at NeurIPS 2021: Benchmarks for EEG Transfer Learning Competition](https://mlsanity.com/paper/2202.03267/) (2022)
- [EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks](https://mlsanity.com/paper/2306.13109/) (2023)
- [Aggregating Intrinsic Information to Enhance BCI Performance through Federated Learning](https://mlsanity.com/paper/2308.11636/) (2023)
- [Motor Imagery Decoding Using Ensemble Curriculum Learning and Collaborative Training](https://mlsanity.com/paper/2211.11460/) (2022)
- [Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation](https://mlsanity.com/paper/2505.17099/) (2025)
- [Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing](https://mlsanity.com/paper/2103.08664/) (2021)
- [Learning aligned EEG representations with subject-specific encoders](https://mlsanity.com/paper/2606.16462/) (2026)
- [Federated deep transfer learning for EEG decoding using multiple BCI tasks](https://mlsanity.com/paper/2211.10976/) (2022)
- [ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification](https://mlsanity.com/paper/2609.33967/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have become a powerful technique to decode EEG and have become the benchmark for motor imagery EEG Brain-Computer-Interface (BCI) decoding. However, it is still challenging to train CNNs on multiple subjects' EEG without decreasing individual performance. This is known as the negative transfer problem, i.e. learning from dissimilar distributions causes CNNs to misrepresent each of them instead of learning a richer representation. As a result, CNNs cannot directly use multiple subjects' EEG to enhance model performance directly. To address this problem, we extend deep transfer learning techniques to the EEG multi-subject training case. We propose a multi-branch deep transfer network, the Separate-Common-Separate Network (SCSN) based on splitting the network's feature extractors for individual subjects. We also explore the possibility of applying Maximum-mean discrepancy (MMD) to the SCSN (SCSN-MMD) to better align distributions of features from individual feature extractors. The proposed network is evaluated on the BCI Competition IV 2a dataset (BCICIV2a dataset) and our online recorded dataset. Results show that the proposed SCSN (81.8%, 53.2%) and SCSN-MMD (81.8%, 54.8%) outperformed the benchmark CNN (73.4%, 48.8%) on both datasets using multiple subjects. Our proposed networks show the potential to utilise larger multi-subject datasets to train an EEG decoder without being influenced by negative transfer.