Network representation learning based on social similarities
Analysis of large-scale networks generally requires mapping high-dimensional network data to a low-dimensional space. We thus need to represent the node and connections accurate and effectively, and representation learning could be a promising method. In this paper, we investigate a novel social sim...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2022.974246/full |
| _version_ | 1818494313730932736 |
|---|---|
| author | Ziwei Mo Zhenzhen Xie Xilian Zhang Qi Luo Yanwei Zheng Dongxiao Yu |
| author_facet | Ziwei Mo Zhenzhen Xie Xilian Zhang Qi Luo Yanwei Zheng Dongxiao Yu |
| author_sort | Ziwei Mo |
| collection | DOAJ |
| description | Analysis of large-scale networks generally requires mapping high-dimensional network data to a low-dimensional space. We thus need to represent the node and connections accurate and effectively, and representation learning could be a promising method. In this paper, we investigate a novel social similarity-based method for learning network representations. We first introduce neighborhood structural features for representing node identities based on higher-order structural parameters. Then the node representations are learned by a random walk approach that based on the structural features. Our proposed truss2vec is able to maintain both structural similarity of nodes and domain similarity. Extensive experiments have shown that our model outperforms the state-of-the-art solutions. |
| first_indexed | 2024-12-10T18:04:56Z |
| format | Article |
| id | doaj.art-383a65acf8544a779ecd29fc4a0567c5 |
| institution | Directory Open Access Journal |
| issn | 2296-665X |
| language | English |
| last_indexed | 2024-12-10T18:04:56Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj.art-383a65acf8544a779ecd29fc4a0567c52022-12-22T01:38:38ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2022-08-011010.3389/fenvs.2022.974246974246Network representation learning based on social similaritiesZiwei MoZhenzhen XieXilian ZhangQi LuoYanwei ZhengDongxiao YuAnalysis of large-scale networks generally requires mapping high-dimensional network data to a low-dimensional space. We thus need to represent the node and connections accurate and effectively, and representation learning could be a promising method. In this paper, we investigate a novel social similarity-based method for learning network representations. We first introduce neighborhood structural features for representing node identities based on higher-order structural parameters. Then the node representations are learned by a random walk approach that based on the structural features. Our proposed truss2vec is able to maintain both structural similarity of nodes and domain similarity. Extensive experiments have shown that our model outperforms the state-of-the-art solutions.https://www.frontiersin.org/articles/10.3389/fenvs.2022.974246/fullsocial networksgraph learningnetwork representationk-trusssocial similarities |
| spellingShingle | Ziwei Mo Zhenzhen Xie Xilian Zhang Qi Luo Yanwei Zheng Dongxiao Yu Network representation learning based on social similarities Frontiers in Environmental Science social networks graph learning network representation k-truss social similarities |
| title | Network representation learning based on social similarities |
| title_full | Network representation learning based on social similarities |
| title_fullStr | Network representation learning based on social similarities |
| title_full_unstemmed | Network representation learning based on social similarities |
| title_short | Network representation learning based on social similarities |
| title_sort | network representation learning based on social similarities |
| topic | social networks graph learning network representation k-truss social similarities |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2022.974246/full |
| work_keys_str_mv | AT ziweimo networkrepresentationlearningbasedonsocialsimilarities AT zhenzhenxie networkrepresentationlearningbasedonsocialsimilarities AT xilianzhang networkrepresentationlearningbasedonsocialsimilarities AT qiluo networkrepresentationlearningbasedonsocialsimilarities AT yanweizheng networkrepresentationlearningbasedonsocialsimilarities AT dongxiaoyu networkrepresentationlearningbasedonsocialsimilarities |