# M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognition

arXiv: https://arxiv.org/abs/2404.15615 · HTML: https://mlsanity.com/paper/2404.15615/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 72 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 16 of 16)

- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [EEG-Based Emotion Recognition Using Regularized Graph Neural Networks](https://mlsanity.com/paper/1907.07835/) (2019)
- [Visual Domain Adaptation with Manifold Embedded Distribution Alignment](https://mlsanity.com/paper/1807.07258/) (2018)
- [Identifying Stable Patterns over Time for Emotion Recognition from EEG](https://mlsanity.com/paper/1601.02197/) (2016)
- [Joint Geometrical and Statistical Alignment for Visual Domain Adaptation](https://mlsanity.com/paper/1705.05498/) (2017)
- [Stratified Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1801.00820/) (2017)
- [Transfer Learning in Brain-Computer Interfaces](https://mlsanity.com/paper/1512.00296/) (2015)
- [Balanced Distribution Adaptation for Transfer Learning](https://mlsanity.com/paper/1807.00516/) (2018)
- [MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition](https://mlsanity.com/paper/2107.07740/) (2021)
- [EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition](https://mlsanity.com/paper/2102.03777/) (2021)
- [EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognition](https://mlsanity.com/paper/2304.06496/) (2023)
- [Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition](https://mlsanity.com/paper/2308.11635/) (2023)
- [A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition](https://mlsanity.com/paper/2009.09585/) (2020)
- [Progressive Graph Convolution Network for EEG Emotion Recognition](https://mlsanity.com/paper/2112.09069/) (2021)

## Built on by (most cited first, 3 of 3)

- [EEG-SCMM: Soft Contrastive Masked Modeling for Cross-Corpus EEG-Based Emotion Recognition](https://mlsanity.com/paper/2408.09186/) (2024)
- [Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition](https://mlsanity.com/paper/2509.01135/) (2025)
- [Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition](https://mlsanity.com/paper/2603.26713/) (2026)

## Abstract (arXiv)

Emotion decoding using Electroencephalography (EEG)-based affective brain-computer interfaces (aBCIs) plays a crucial role in affective computing but is limited by challenges such as EEG's non-stationarity, individual variability, and the high cost of large labeled datasets. While deep learning methods are effective, they require extensive computational resources and large data volumes, limiting their practical application. To overcome these issues, we propose Manifold-based Domain Adaptation with Dynamic Distribution (M3D), a lightweight, non-deep transfer learning framework. M3D consists of four key modules: manifold feature transformation, dynamic distribution alignment, classifier learning, and ensemble learning. The data is mapped to an optimal Grassmann manifold space, enabling dynamic alignment of source and target domains. This alignment is designed to prioritize both marginal and conditional distributions, improving adaptation efficiency across diverse datasets. In classifier learning, the principle of structural risk minimization is applied to build robust classification models. Additionally, dynamic distribution alignment iteratively refines the classifier. The ensemble learning module aggregates classifiers from different optimization stages to leverage diversity and enhance prediction accuracy. M3D is evaluated on two EEG emotion recognition datasets using two validation protocols (cross-subject single-session and cross-subject cross-session) and a clinical EEG dataset for Major Depressive Disorder (MDD). Experimental results show that M3D outperforms traditional non-deep learning methods with a 4.47% average improvement and achieves deep learning-level performance with reduced data and computational requirements, demonstrating its potential for real-world aBCI applications.