Learning attribute network algorithm based on high-order similarity
Due to the lack of deep-level information mining and utilization in the existing network representation learning methods,the potential pattern structure similarity was proposed by further exploring the potential information in the network.The similarity score between network structures was defined t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2020-12-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020309/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841528930730770432 |
|---|---|
| author | Shaoqing WU Yihong DONG Xiong WANG Yan CAO Yu XIN |
| author_facet | Shaoqing WU Yihong DONG Xiong WANG Yan CAO Yu XIN |
| author_sort | Shaoqing WU |
| collection | DOAJ |
| description | Due to the lack of deep-level information mining and utilization in the existing network representation learning methods,the potential pattern structure similarity was proposed by further exploring the potential information in the network.The similarity score between network structures was defined to measure the similarity between various structures so that nodes could cross irrelevant vertices to obtain high-order similarities on the global structure.In order to achieve the best effect,deep learning was used to fuse multiple information sources to participate in training together to make up for the deficiency of random walks.In the experiment,Lap,DeepWalk,TADW,SDNE and CANE were selected as comparison methods,and three real-world networks were used as data sets to verify the validity of the model,and experiments of node classification and link reconstruction are carried out.In the node classification,the average performance is improved by 1.7 percentage points for different datasets and training proportions.In the link reconstruction experiment,only half the dimension is needed to achieve better performance.Finally,the performance improvement of the model under different network depths was discussed.By increasing the depth of the model,the average performance of node classification increased by 1.1 percentage points. |
| format | Article |
| id | doaj-art-3ffba60cf142416da863cc59d3f313ed |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2020-12-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-3ffba60cf142416da863cc59d3f313ed2025-01-15T03:32:13ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012020-12-0136203259813516Learning attribute network algorithm based on high-order similarityShaoqing WUYihong DONGXiong WANGYan CAOYu XINDue to the lack of deep-level information mining and utilization in the existing network representation learning methods,the potential pattern structure similarity was proposed by further exploring the potential information in the network.The similarity score between network structures was defined to measure the similarity between various structures so that nodes could cross irrelevant vertices to obtain high-order similarities on the global structure.In order to achieve the best effect,deep learning was used to fuse multiple information sources to participate in training together to make up for the deficiency of random walks.In the experiment,Lap,DeepWalk,TADW,SDNE and CANE were selected as comparison methods,and three real-world networks were used as data sets to verify the validity of the model,and experiments of node classification and link reconstruction are carried out.In the node classification,the average performance is improved by 1.7 percentage points for different datasets and training proportions.In the link reconstruction experiment,only half the dimension is needed to achieve better performance.Finally,the performance improvement of the model under different network depths was discussed.By increasing the depth of the model,the average performance of node classification increased by 1.1 percentage points.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020309/network representation learninggraph embeddingattribute networkstructure information |
| spellingShingle | Shaoqing WU Yihong DONG Xiong WANG Yan CAO Yu XIN Learning attribute network algorithm based on high-order similarity Dianxin kexue network representation learning graph embedding attribute network structure information |
| title | Learning attribute network algorithm based on high-order similarity |
| title_full | Learning attribute network algorithm based on high-order similarity |
| title_fullStr | Learning attribute network algorithm based on high-order similarity |
| title_full_unstemmed | Learning attribute network algorithm based on high-order similarity |
| title_short | Learning attribute network algorithm based on high-order similarity |
| title_sort | learning attribute network algorithm based on high order similarity |
| topic | network representation learning graph embedding attribute network structure information |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020309/ |
| work_keys_str_mv | AT shaoqingwu learningattributenetworkalgorithmbasedonhighordersimilarity AT yihongdong learningattributenetworkalgorithmbasedonhighordersimilarity AT xiongwang learningattributenetworkalgorithmbasedonhighordersimilarity AT yancao learningattributenetworkalgorithmbasedonhighordersimilarity AT yuxin learningattributenetworkalgorithmbasedonhighordersimilarity |