将大模型语义融入脑网络分析，提升疾病诊断准确率与可解释性。
SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs
- 用全局自注意力融合区域语义，增强节点表征
- 构建多尺度超图，捕捉高阶功能关联与子网络结构
- 决策层注入患者文本嵌入，直接指导预测结果
有效的脑疾病诊断需要脑连接模式与高层语义知识的协同。现有方法多将大语言模型（LLM）生成的语义作为辅助特征或监督信号，限制其在决策中的直接作用，影响分类的稳定性和鲁棒性。为此，本文提出SABER框架，主动将LLM衍生语义融入预测过程：首先通过全局自注意力在ROI层面融合语义，丰富节点表征并提供全脑上下文；其次构建多尺度超图，显式建模功能子网络与多区域交互，克服传统GNN的局部性局限，捕捉高阶依赖关系；最后设计决策层语义对齐机制，选择性地将患者特异性文本嵌入注入图表示，使语义直接引导预测而不扰动底层网络结构。在ABIDE和ADHD-200公开脑网络数据集上的实验表明，该方法达到领先性能，显著提升稳定性与可解释性，尤其在小样本场景下表现优异。
原文摘要 · Abstract (English)
Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level semantic knowledge. Existing methods, however, largely treat semantics from large language models (LLMs) as auxiliary features or supervision, limiting their direct role in decision-making and constraining classification stability and robustness. To overcome this, we propose a semantic-aligned brain network framework that actively integrates LLM-derived semantics into the prediction process. Specifically, ROI-level semantics are first incorporated via global self-attention to enrich node representations and provide whole-brain context. Multi-scale hypergraphs are then constructed to explicitly model functional subnetworks and multi-ROI interactions, addressing the locality limitations of traditional GNNs and capturing high-order dependencies. Finally, a decision-level semantic alignment mechanism selectively injects patient-specific textual embeddings into graph representations, enabling semantics to directly guide predictions without perturbing the underlying network structure. Experiments on public brain network datasets ABIDE and ADHD-200 demonstrate state-of-the-art performance, enhanced stability, and improved interpretability, particularly in small-sample settings.
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。