The figure prompts a learning method and device, electronic equipment, storage medium and program product

By introducing a dual-cue framework of local and global cue vectors, the contradiction between local and global information modeling in existing technologies is resolved, enabling efficient information utilization and performance improvement in complex downstream tasks.

CN122173692APending Publication Date: 2026-06-09BEIJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING UNIV OF POSTS & TELECOMM
Filing Date
2026-01-20
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

In existing graph hint learning methods, local structure models struggle to capture high-order structural information, and introducing global attention mechanisms can easily lead to over-globalization, resulting in weakened local semantics or viewpoint conflicts, making it difficult to realize their potential in complex downstream tasks.

Method used

By introducing local and global cue vectors, the local structural features and global dependencies of graph data are captured respectively. The node embeddings are fused using contrastive learning and distribution alignment mechanisms to form a dual-cue task inference model.

Benefits of technology

Without large-scale full-scale fine-tuning, it fully utilizes local and global information from the graph to improve the performance of downstream tasks, particularly in applications such as drug molecule design, medical image analysis, and bioinformatics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122173692A_ABST
    Figure CN122173692A_ABST
Patent Text Reader

Abstract

This disclosure provides a graph cue learning method, apparatus, electronic device, storage medium, and program product. The method includes: determining the graph structure data of a target network; extracting vectors from the graph structure data to obtain local cue vectors and global cue vectors; enhancing the local and global cue vectors to obtain local and global cue-enhanced node embeddings; training a model based on the local and global cue-enhanced node embeddings to obtain a dual-cue task inference model; and inputting the graph structure data into the dual-cue task inference model for task inference to obtain the task classification result output by the model. This disclosure can fully utilize graph structure information and improve downstream task performance with only a few parameter updates.
Need to check novelty before this filing date? Find Prior Art