Parallel constraint subgraph mining method based on edge-node mixed segmentation
A hybrid graph and node collection technology, which is applied in energy-saving computing, climate sustainability, and other database retrieval, can solve problems such as node redundancy, poor algorithm scalability, and disrupted load balance, and reduce segmentation redundancy , The effect of improving the efficiency of computing tasks
Pending Publication Date: 2022-07-08
ZHEJIANG LAB
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the irregular nature of graph data, the constrained subgraph calculation based on the classical parallel framework often destroys the load balance due to the unbalanced subgraph segmentation, resulting in poor scalability of the algorithm
[0003] Common subgraph segmentation methods, node-based subgraph segmentation methods usually cut off edges, resulting in information loss; edge-based subgraph segmentation will cause node redundancy
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] In order to make the objectives, technical solutions and technical effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments of the description.
[0042] like figure 1 As shown, the parallel constrained subgraph mining method based on edge-node hybrid segmentation of the present invention includes the following steps:
[0043] S1, graph data input;
[0044] S2, edge-node hybrid graph data segmentation;
[0045] S3. Distribute computing tasks;
[0046] S4. Execute parallel computing.
[0047] like figure 2 As shown, the graph data segmentation steps of step S2 are as follows:
[0048] 1) For the graph data input by S1, calculate the embedded representation vector of each graph node;
[0049] 2) Calculate the edge weight for each edge in the graph;
[0050] 3) Calculate the segmentation index H of all nodes in the graph;
[0051] 4) According to the segment...
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
Login to View More Abstract
The invention belongs to the technical field of graph data mining calculation, and particularly relates to a parallel constraint subgraph mining method based on edge-node mixed segmentation, which comprises the following steps of: S1, inputting graph data; s2, edge-node mixed graph data segmentation is carried out; s3, distributing a calculation task; and S4, executing parallel computing. According to the method, in the aspect of graph data segmentation, an edge node mixed sub-graph segmentation scheme is adopted, the integrity of the sub-graphs and the balance of segmentation are considered in a constraint sub-graph mining task, and meanwhile segmentation redundancy is reduced; in the aspect of constraint subgraph mining, a parallel computing framework is adopted to improve the computing task efficiency.
Description
technical field [0001] The invention belongs to the technical field of graph data mining computing, in particular to a parallel constraint subgraph mining method based on edge-node hybrid segmentation. Background technique [0002] The computational problem of constrained subgraphs has been studied since the 1960s. Faced with massive graph data, how to mine subgraphs that satisfy constraints is the main research content of constrained subgraph mining. Part of the research work attempts to use I / O and memory optimization techniques to improve the performance of single-computer computing and the upper limit of the computing scale, and the other part of the work is to formulate constrained subgraph computing schemes under the classical parallel framework. The commonly used distributed frameworks are MapReduce and Parallel computing framework based on MPI communication protocol. Due to the irregular nature of graph data, the constrained subgraph computation based on the classi...
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
Login to View More IPC IPC(8): G06F16/901G06F16/903
CPCG06F16/9024G06F16/90335G06F2216/03Y02D10/00
Inventor 许增辉张阳余亭张吉
Owner ZHEJIANG LAB