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 down... Activation: multi-modal fusion, mixture-of-experts, MoE, brain network, SC-FC fusion, sample-adaptive
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 and dynamically fuse them based on sample-specific characteristics. This approach enables the model to adapt its computation to individual samples, leading to improved performance in brain network analysis tasks such as classification and prediction.
Dynamic MoE-based fusion for SC and FC modalities
The paper tackles fundamental challenges in brain signal analysis and decoding, proposing novel solutions that advance the state-of-the-art.
Sample-adaptive brain network classification
This work builds upon and extends:
Generated from arXiv paper on 2026-04-12
execreadwriteUser: 请帮我应用此技能
Agent: 我将按照标准流程执行...
User: 有更复杂的场景需要处理
Agent: 针对复杂场景，我将采用以下策略...