Heterogeneous graph construction and node representation learning method of Treatise on Febrile Diseases based on graph convolutional network
Objective: To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) dataset and explore an optimal learning method represented with node attributes based on graph convolutional network (GCN). Methods: Clauses that contain symptoms, formulas...
Main Authors: | Junfeng YAN, Zhihua WEN, Beiji ZOU |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2022-12-01
|
Series: | Digital Chinese Medicine |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2589377722000775 |
Similar Items
-
Construction and application of knowledge graph of Treatise on Febrile Diseases
by: Dongbo LIU, et al.
Published: (2022-12-01) -
Multi-view Heterogeneous Graph Neural Networks for Node Classification
by: Xi Zeng, et al.
Published: (2024-06-01) -
Convolution Based Graph Representation Learning from the Perspective of High Order Node Similarities
by: Xing Li, et al.
Published: (2022-12-01) -
Heterogeneous Graph Purification Network: Purifying Noisy Heterogeneity without Metapaths
by: Sirui Shen, et al.
Published: (2023-03-01) -
Scalably Using Node Attributes and Graph Structure for Node Classification
by: Arpit Merchant, et al.
Published: (2022-06-01)