图节点分类模型训练方法、装置、电子设备及存储介质
By using an alternating iterative training method for graph structure features and graph node features, a target graph node classification model is generated, which solves the problem of insufficient model accuracy in existing technologies and achieves higher classification accuracy and a simplified training process.
CN116433953BActive Publication Date: 2026-07-17SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
- Filing Date
- 2021-12-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In existing technologies, the accuracy of algorithms that consider graph structure features or graph node features alone is weakened, and they cannot effectively combine the two types of features for graph node classification.
Method used
By iteratively training the initial graph node classification network using graph structure features and graph node features alternately, the target graph node classification model is generated, ensuring that the model learns both graph node features and graph structure features.
Benefits of technology
It improves the accuracy of graph node classification models, simplifies the training process, and ensures both the complexity of the model and the accuracy of the classification results.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116433953B_ABST
Abstract
本发明揭示了一种图节点分类模型训练方法、装置、电子设备及存储介质，本发明涉及模型训练领域，该方法包括：获取样本数据；基于样本数据构建图节点特征和图结构特征；依次利用图结构特征以及图节点特征交替迭代训练初始图节点分类网络，以确定目标图节点分类模型。上述方法，通过依次利用图结构特征以及图节点特征交替迭代训练初始图节点分类网络，使得目标图节点分类模型训练过程中既充分学习了图节点特征也充分学习了图结构特征，提高了目标图节点分类模型的精准度。使得上述方法中的目标图节点分类模型不仅可以完成图的节点分类，还可以保证分类结果的准确性。
Need to check novelty before this filing date? Find Prior Art