用脑网络先验指导专家模型，实现可解释的脑图像重建。
FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding
- 将不同脑网络作为专业专家，动态路由融合其贡献。
- 仅用0.68B参数即达到顶尖语义重建效果。
- 揭示脑网络与语义处理的生物合理性对应，适合神经科学与AI交叉研究者。
从功能磁共振成像（fMRI）中重建视觉图像是一项基础性的脑解码任务，有助于理解人类感知机制并推动脑机接口（BCI）的发展。然而，现有方法通常将局部视觉皮层的fMRI信号展平为一维（1D）向量，直接映射到如对比语言-图像预训练（CLIP）等潜在空间，这种范式不仅破坏了大脑固有的网络拓扑结构，导致神经科学可解释性有限，还忽视了其他分布式功能网络在高层次视觉语义处理中的协同作用。为此，我们提出FPED——一种功能网络先验引导的混合专家（MoE）框架，用于可解释的脑解码。该框架显式将不同功能脑网络建模为专业化专家，并采用自适应路由机制捕捉它们对视觉语义理解的互补贡献。不同于传统同质解码范式，我们的框架引入神经生物学合理先验，实现结构化且可解释的网络级表征学习。实验表明，FPED仅使用0.68B参数便实现了极具竞争力的语义重建性能。所学习的路由动态揭示了功能脑网络与模态特定语义处理之间的生物学意义对应关系，提供了透明的神经科学可解释性。这表明，考虑脑网络结构的专家建模是连接神经解码与生物启发式人工智能的有前景方向。
原文摘要 · Abstract (English)
Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for understanding human perceptual mechanisms and developing advanced brain-computer interfaces (BCIs). However, most current methods simply flatten fMRI signals from localized visual cortices into one-dimensional (1D) vectors, mapping them directly into latent spaces such as that of Contrastive Language-Image Pre-training (CLIP). This paradigm not only disrupts the inherent network topology of the brain-leading to limited neuroscientific interpretability-but also overlooks the synergistic contributions of other distributed functional networks in processing high-level visual semantics. To address these limitations, we propose FPED, a Functional-Network Prior-Guided Mixture of Experts (MoE) framework for interpretable brain decoding. FPED explicitly models different functional brain networks as specialized experts and employs adaptive routing to capture their complementary contributions to visual semantic understanding. Unlike conventional homogeneous decoding paradigms, our framework incorporates neurobiologically grounded priors to enable structured and interpretable network-level representation learning. Experimental results demonstrate that FPED achieves highly competitive semantic reconstruction performance with only 0.68B parameters. The learned routing dynamics reveal biologically meaningful correspondence between functional brain networks and modality-specific semantic processing, providing transparent neuroscientific interpretability. This suggests that brain network-aware expert modeling is a promising direction for bridging neural decoding and biologically inspired artificial intelligence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。