arXiv：cs.LG· Siyu Liu, Guangqi Wen, Peng Cao, Jinzhu Yang, Xiaoli Liu, Fei Wang, Osmar R. Zaiane·· 5 小时前AI 评分29
KD-Brain：用先验知识图学习探索异质脑网络的子网络交互
Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning
AI 导读
针对 Transformer 方法在训练样本有限时难以学习子网络交互的问题，研究者提出 KD-Brain 先验知识图学习框架，通过语义条件交互机制将语义先验注入注意力查询，并用病理一致性约束对齐临床先验。该框架在多种精神障碍诊断任务上取得 SOTA，并识别出与精神病理生理一致的可解释生物标志物，代码已开源。
正文
Abstract:Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing Transformer-based methods due to the limited number of training samples. To address these challenges, we propose KD-Brain, a Prior-Informed Graph Learning framework for explicitly encoding prior knowledge to guide the learning process. Specifically, we design a Semantic-Conditioned Interaction mechanism that injects semantic priors into the attention query, explicitly navigating the subnetwork interactions based on their functional identities. Furthermore, we introduce a Pathology-Consistent Constraint, which regularizes the model optimization by aligning the learned interaction distributions with clinical priors. Additionally, KD-Brain leads to state-of-the-art performance on a wide range of disorder diagnosis tasks and identifies interpretable biomarkers consistent with psychiatric pathophysiology. Our code is available at this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.19307 [cs.LG] |
| (or arXiv:2603.19307v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.19307 arXiv-issued DOI via DataCite |
Submission history
From: Siyu Liu [view email]
[v1]
Fri, 13 Mar 2026 12:04:23 UTC (18,533 KB)
[v2]
Fri, 2 Oct 2026 05:13:31 UTC (3,015 KB)
来源：arXiv：cs.LG · arxiv.org