General distributed graph processing method and system based on reinforcement learning

A reinforcement learning and distributed technology, applied in machine learning, special data processing applications, instruments, etc., can solve the problems of single use scene and poor segmentation effect.

Active Publication Date: 2020-08-14
SHENZHEN UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Therefore, the technical problem to be solved by the present invention is to overcome the defects that the graph cutting model in the prior art is easy to fall into a local optim

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • General distributed graph processing method and system based on reinforcement learning
  • General distributed graph processing method and system based on reinforcement learning
  • General distributed graph processing method and system based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] Embodiments of the present invention provide a general distributed graph processing method based on reinforcement learning, which can be applied to different optimization objectives, for example, in problems such as performance and cost optimization, load balancing, and performance optimization of geographically distributed graph processing systems, such as figure 1 shown, including the following steps:

[0086] Step S10: Define a distributed data processing center based on graph theory to form a distributed graph, use a preset graph cutting model and a preset graph processing model, and preset constraints based on preset constraints to cut the distributed graph.

[0087]The embodiment of the present invention takes the geographically distributed graph segmentation processing process as an example, assuming that the vertex data is not backed up on the data processing center (hereinafter referred to as DC), and one machine can only execute the graph processing task of one...

Embodiment 2

[0151] Embodiments of the present invention provide a general distributed graph processing system based on reinforcement learning, such as image 3 shown, including:

[0152] The distributed graph definition and constraint setting module 10 is used to define a distributed data processing center based on graph theory to form a distributed graph, and use a preset graph cutting model and a preset graph processing model to process the distributed graph based on preset constraints cutting. This module executes the method described in step S10 in Embodiment 1, which will not be repeated here.

[0153] The action selection module 11 is used to assign a learning automaton to each vertex of the distributed graph, initialize the probability of each vertex in each data processing center, and based on the initialized probability, the learning automaton is selected according to a preset action method Select the data processing center with the highest probability for the vertex. This mod...

Embodiment 3

[0161] An embodiment of the present invention provides a computer device, such as Figure 4 As shown, the device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected via a bus or in other ways, Figure 4 Take connection via bus as an example.

[0162] The processor 51 may be a central processing unit (Central Processing Unit, CPU). Processor 51 can also be other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.

[0163] As a non-transitory computer-readable storage medium, the memory 52 can be used to store non-transitory software programs, non-transitory computer-exe...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a general distributed graph processing method and system based on reinforcement learning. The method includes: defining a distributed data processing center based on a graph theory to form a distributed graph; utilizing a preset graph cutting model and a preset graph processing model to cut the distributed graph by utilizing a reinforcement learning mode based on a preset constraint condition; allocating a learning automaton to each vertex; finding the most suitable data processing center for the vertex through training, wherein the possibility of each vertex in all data processing centers obeys certain probability distribution, the whole system comprises five steps of action selection, vertex migration, score calculation, enhanced signal calculation and probabilityupdating in each iteration process, and the iteration is judged to be ended when the maximum iteration frequency is reached or the constraint condition is converged. The distributed graph processingmodel formed by the universal distributed graph processing method provided by the invention is a universal distributed graph model, and only different score calculation schemes and different weight vectors need to be designed for different optimization targets.

Description

technical field [0001] The invention relates to the field of large-scale graph segmentation processing, in particular to a general distributed graph processing method and system based on reinforcement learning. Background technique [0002] In order to efficiently process large-scale graphs, it is usually necessary to partition the graph so that the partitioned subgraphs can be processed in parallel. There are currently several classic models for large-scale graph segmentation: [0003] Heuristic model. The traditional mainstream large-scale graph processing systems Pregel and PowerGraph all use heuristic segmentation algorithms. The default partition method of Pregel is to achieve the optimization goal of enhancing the locality of the partition and reducing the network traffic between computing nodes by performing a modulo operation on the Hash value of the vertex id. By default, PowerGraph adopts the greedy point segmentation method. For a newly added edge, if a vertex o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N20/00G06F16/901
CPCG06N20/00G06F16/9024Y02D10/00
Inventor 周池罗鹃云毛睿
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap