Random discarding method and system of graph neural network based on dynamic discarding
By introducing dynamic drop rate and stopping random drop rules in graph neural networks, the problems of overfitting, oversmoothing and high computational cost of GCN on large-scale graphs are solved, and higher accuracy and robustness are achieved.
CN119646481APending Publication Date: 2025-03-18NANJING UNIV OF INFORMATION SCI & TECH
0 Cites 1 Cited by
Patent Information
- Application Number
- CN202411697459.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-18
AI Technical Summary
Technical Problem
GCN is prone to overfitting, oversmoothing and state-time and space-time explosions in training on large-scale graphs, resulting in poor performance of the model on test data.
Method used
The random discarding method based on dynamic discarding graph neural network is adopted to alleviate the oversmoothing problem and improve the accuracy and robustness of the model by dynamically adjusting the discarding rate and stopping the random discarding rules.
Benefits of technology
It effectively alleviates the oversmoothing problem, improves the accuracy and robustness of the model, and reduces calculation costs.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses a random discarding method and system for a graph neural network based on dynamic discarding, and relates to the technical field of artificial intelligence, and the method comprises the following steps: receiving a to-be-processed representative graph, carrying out the node feature extraction of the to-be-processed representative graph, obtaining a node receiving matrix, carrying out the normalization of the node receiving matrix, and obtaining a normalized matrix; extracting a feature vector matrix and a feature value diagonal matrix based on the normalized matrix, and calculating a message transfer matrix based on the feature vector matrix and the feature value diagonal matrix; the message passing matrix is input into a pre-established graph neural network model based on dynamic discarding, information discarding is carried out on the message passing matrix, a discarded message passing matrix is obtained through output, and the pre-established graph neural network model based on dynamic discarding is trained based on a random discarding stopping rule.
Need to check novelty before this filing date? Find Prior Art