# BrainMAE: A Region-aware Self-supervised Learning Framework for Brain Signals

arXiv: https://arxiv.org/abs/2406.17086 · HTML: https://mlsanity.com/paper/2406.17086/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 58 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [BEVT: BERT Pretraining of Video Transformers](https://mlsanity.com/paper/2112.01529/) (2021)
- [Brain Network Transformer](https://mlsanity.com/paper/2210.06681/) (2022)
- [Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention](https://mlsanity.com/paper/2105.13495/) (2021)
- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation](https://mlsanity.com/paper/2205.12465/) (2022)
- [Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis](https://mlsanity.com/paper/2207.00813/) (2022)
- [Graph Neural Network for Interpreting Task-fMRI Biomarkers](https://mlsanity.com/paper/1907.01661/) (2019)
- [Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data](https://mlsanity.com/paper/2206.11417/) (2022)
- [NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics](https://mlsanity.com/paper/2306.06202/) (2023)
- [Fine-grain atlases of functional modes for fMRI analysis](https://mlsanity.com/paper/2003.05405/) (2020)
- [Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis](https://mlsanity.com/paper/2007.14589/) (2020)
- [The Dynamics of Functional Brain Networks: Integrated Network States during Cognitive Function](https://mlsanity.com/paper/1511.02976/) (2015)
- [Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning](https://mlsanity.com/paper/2206.04486/) (2022)

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

- [Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery](https://mlsanity.com/paper/2503.00580/) (2025)
- [BrainNetMLP: An Efficient and Effective Baseline for Functional Brain Network Classification](https://mlsanity.com/paper/2505.11538/) (2025)
- [Bridging Brain with Foundation Models through Self-Supervised Learning](https://mlsanity.com/paper/2506.16009/) (2025)
- [Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2605.14569/) (2026)
- [Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI](https://mlsanity.com/paper/2605.01240/) (2026)
- [Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs](https://mlsanity.com/paper/2605.18172/) (2026)

## Abstract (arXiv)

The human brain is a complex, dynamic network, which is commonly studied using functional magnetic resonance imaging (fMRI) and modeled as network of Regions of interest (ROIs) for understanding various brain functions. Recent studies utilize deep learning approaches to learn the brain network representation based on functional connectivity (FC) profile, broadly falling into two main categories. The Fixed-FC approaches, utilizing the FC profile which represents the linear temporal relation within the brain network, are limited by failing to capture informative brain temporal dynamics. On the other hand, the Dynamic-FC approaches, modeling the evolving FC profile over time, often exhibit less satisfactory performance due to challenges in handling the inherent noisy nature of fMRI data. To address these challenges, we propose Brain Masked Auto-Encoder (BrainMAE) for learning representations directly from fMRI time-series data. Our approach incorporates two essential components: a region-aware graph attention mechanism designed to capture the relationships between different brain ROIs, and a novel self-supervised masked autoencoding framework for effective model pre-training. These components enable the model to capture rich temporal dynamics of brain activity while maintaining resilience to inherent noise in fMRI data. Our experiments demonstrate that BrainMAE consistently outperforms established baseline methods by significant margins in four distinct downstream tasks. Finally, leveraging the model's inherent interpretability, our analysis of model-generated representations reveals findings that resonate with ongoing research in the field of neuroscience.