# Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing

arXiv: https://arxiv.org/abs/2510.22197 · HTML: https://mlsanity.com/paper/2510.22197/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 25 Oct 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data](https://mlsanity.com/paper/2101.12037/) (2021)
- [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition](https://mlsanity.com/paper/2109.09559/) (2021)
- [Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery](https://mlsanity.com/paper/2503.00580/) (2025)
- [Geodesic Optimization for Predictive Shift Adaptation on EEG data](https://mlsanity.com/paper/2407.03878/) (2024)
- [Joint Contrastive Learning with Feature Alignment for Cross-Corpus EEG-based Emotion Recognition](https://mlsanity.com/paper/2404.09559/) (2024)
- [Dynamic-Attention-based EEG State Transition Modeling for Emotion Recognition](https://mlsanity.com/paper/2411.04568/) (2024)
- [Enhancing Cross-Dataset EEG Emotion Recognition: A Novel Approach with Emotional EEG Style Transfer Network](https://mlsanity.com/paper/2403.16540/) (2024)
- [EEG-SCMM: Soft Contrastive Masked Modeling for Cross-Corpus EEG-Based Emotion Recognition](https://mlsanity.com/paper/2408.09186/) (2024)
- [Enhanced Cross-Dataset Electroencephalogram-based Emotion Recognition using Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.12852/) (2024)

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

- [CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG](https://mlsanity.com/paper/2602.19138/) (2026)
- [RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning](https://mlsanity.com/paper/2606.15278/) (2026)
- [Benchmarking EEG Foundation Models at Scale: Lessons from 20,000 Evaluations](https://mlsanity.com/paper/2609.32743/) (2026)

## Abstract (arXiv)

Task-specific pre-training is essential when task representations diverge from generic pre-training features. Existing task-general pre-training EEG models struggle with complex tasks like emotion recognition due to mismatches between task-specific features and broad pre-training approaches. This work aims to develop a task-specific multi-dataset joint pre-training framework for cross-dataset emotion recognition, tackling problems of large inter-dataset distribution shifts, inconsistent emotion category definitions, and substantial inter-subject variability. We introduce a cross-dataset covariance alignment loss to align second-order statistical properties across datasets, enabling robust generalization without the need for extensive labels or per-subject calibration. To capture the long-term dependency and complex dynamics of EEG, we propose a hybrid encoder combining a Mamba-like linear attention channel encoder and a spatiotemporal dynamics model. Our method outperforms state-of-the-art large-scale EEG models by an average of 4.57% in AUROC for few-shot emotion recognition and 11.92% in accuracy for zero-shot generalization to a new dataset. Performance scales with the increase of datasets used in pre-training. Multi-dataset joint pre-training achieves a performance gain of 8.55% over single-dataset training. This work provides a scalable framework for task-specific pre-training and highlights its benefit in generalizable affective computing. Our code is available at https://github.com/ncclab-sustech/mdJPT_nips2025.