Graph neural network data sampling method and device, equipment and storage medium
A technology of data sampling and neural network, applied in biological neural network models, processor architecture/configuration, instruments, etc., can solve problems such as time complexity increase, poor data locality, long sampling time and calculation time, etc., to improve data locality sex, efficiency-enhancing effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] At present, the existing sub-graph sampling methods for accelerated Graph Neural Network (GNN) training mainly include the pipeline overlapping method and the multi-process sampling method; wherein, the pipeline overlapping method refers to: performing sub-graph sampling on the CPU, and performing sub-graph sampling on the CPU. The GPU performs graph neural network model calculations, and the two run in a pipelined manner. This can overlap the sampling time of some subimages. However, the disadvantage of this method is that due to the random memory access and exponentially expanded neighborhood during sampling, the subgraph sampling time is much longer than the calculation time of the graph neural network model, resulting in very unbalanced pipeline units and affecting the efficiency of pipeline operation. The multi-process sampling method means that some graph neural network training frameworks use a multi-process sampling method based on the CPU-GPU pipeline training ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com