Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.19307 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915876223057920 |
|---|---|
| author | Liu, Siyu Wen, Guangqi Cao, Peng Yang, Jinzhu Liu, Xiaoli Wang, Fei Zaiane, Osmar R. |
| author_facet | Liu, Siyu Wen, Guangqi Cao, Peng Yang, Jinzhu Liu, Xiaoli Wang, Fei Zaiane, Osmar R. |
| contents | 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 https://anonymous.4open.science/r/KDBrain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19307 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning Liu, Siyu Wen, Guangqi Cao, Peng Yang, Jinzhu Liu, Xiaoli Wang, Fei Zaiane, Osmar R. Machine Learning Artificial Intelligence 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 https://anonymous.4open.science/r/KDBrain. |
| title | Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.19307 |