# M3D-BFS: a Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis

arXiv: https://arxiv.org/abs/2604.01667 · HTML: https://mlsanity.com/paper/2604.01667/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [On the Representation Collapse of Sparse Mixture of Experts](https://mlsanity.com/paper/2204.09179/) (2022)
- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion](https://mlsanity.com/paper/2302.01392/) (2023)
- [On Uni-Modal Feature Learning in Supervised Multi-Modal Learning](https://mlsanity.com/paper/2305.01233/) (2023)
- [EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE](https://mlsanity.com/paper/2308.11971/) (2023)
- [BrainNPT: Pre-training of Transformer networks for brain network classification](https://mlsanity.com/paper/2305.01666/) (2023)
- [NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomes](https://mlsanity.com/paper/2409.17510/) (2024)
- [Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity](https://mlsanity.com/paper/2209.07811/) (2022)

## Built on by (most cited first, 1 of 1)

- [When Language Models Meet NeuroGraphs: Exploring Enhanced Agentic LLM Framework Towards Brain Network Analysis](https://mlsanity.com/paper/2607.22082/) (2026)

## Abstract (arXiv)

Multi-modal fusion is of great significance in neuroscience which integrates information from different modalities and can achieve better performance than uni-modal methods in downstream tasks. Current multi-modal fusion methods in brain networks, which mainly focus on structural connectivity (SC) and functional connectivity (FC) modalities, are static in nature. They feed different samples into the same model with identical computation, ignoring inherent difference between input samples. This lack of sample adaptation hinders model's further performance. To this end, we innovatively propose a multi-stage dynamic fusion strategy (M3D-BFS) for sample-adaptive multi-modal brain network analysis. Unlike other static fusion methods, we design different mixture-of-experts (MoEs) for uni- and multi-modal representations where modules can adaptively change as input sample changes during inference. To alleviate issue of MoE where training of experts may be collapsed, we divide our method into 3 stages. We first train uni-modal encoders respectively, then pretrain single experts of MoEs before finally finetuning the whole model. A multi-modal disentanglement loss is designed to enhance the final representations. To the best of our knowledge, this is the first work for dynamic fusion for multi-modal brain network analysis. Extensive experiments on different real-world datasets demonstrates the superiority of M3D-BFS.