Structural Hierarchy-Enhanced Network Representation Learning
Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding spac...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/20/7214 |
| _version_ | 1797550797404241920 |
|---|---|
| author | Cheng-Te Li Hong-Yu Lin |
| author_facet | Cheng-Te Li Hong-Yu Lin |
| author_sort | Cheng-Te Li |
| collection | DOAJ |
| description | Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding space, nor model coarse-grained community knowledge hidden behind the network topology. In this paper, we propose a novel NRL framework, Structural Hierarchy Enhancement (SHE), to deal with such two issues. The main idea is to construct a structural hierarchy from the network based on community detection, and to utilize such a hierarchy to perform level-wise NRL. In addition, lower-level node embeddings are passed to higher-level ones so that community knowledge can be aware of in NRL. Experiments conducted on benchmark network datasets show that SHE can significantly boost the performance of NRL in both tasks of NC and LP, compared to other hierarchical NRL methods. |
| first_indexed | 2024-03-10T15:34:31Z |
| format | Article |
| id | doaj.art-6f366aaa283f48bfab5b2e4307a00269 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:34:31Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6f366aaa283f48bfab5b2e4307a002692023-11-20T17:19:18ZengMDPI AGApplied Sciences2076-34172020-10-011020721410.3390/app10207214Structural Hierarchy-Enhanced Network Representation LearningCheng-Te Li0Hong-Yu Lin1Institute of Data Science, National Cheng Kung University, Tainan 70101, TaiwanDepartment of Statistics, National Cheng Kung University, Tainan 70101, TaiwanNetwork representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding space, nor model coarse-grained community knowledge hidden behind the network topology. In this paper, we propose a novel NRL framework, Structural Hierarchy Enhancement (SHE), to deal with such two issues. The main idea is to construct a structural hierarchy from the network based on community detection, and to utilize such a hierarchy to perform level-wise NRL. In addition, lower-level node embeddings are passed to higher-level ones so that community knowledge can be aware of in NRL. Experiments conducted on benchmark network datasets show that SHE can significantly boost the performance of NRL in both tasks of NC and LP, compared to other hierarchical NRL methods.https://www.mdpi.com/2076-3417/10/20/7214network representation learningnode embeddingscommunity detectionstructural hierarchynode classificationlink prediction |
| spellingShingle | Cheng-Te Li Hong-Yu Lin Structural Hierarchy-Enhanced Network Representation Learning Applied Sciences network representation learning node embeddings community detection structural hierarchy node classification link prediction |
| title | Structural Hierarchy-Enhanced Network Representation Learning |
| title_full | Structural Hierarchy-Enhanced Network Representation Learning |
| title_fullStr | Structural Hierarchy-Enhanced Network Representation Learning |
| title_full_unstemmed | Structural Hierarchy-Enhanced Network Representation Learning |
| title_short | Structural Hierarchy-Enhanced Network Representation Learning |
| title_sort | structural hierarchy enhanced network representation learning |
| topic | network representation learning node embeddings community detection structural hierarchy node classification link prediction |
| url | https://www.mdpi.com/2076-3417/10/20/7214 |
| work_keys_str_mv | AT chengteli structuralhierarchyenhancednetworkrepresentationlearning AT hongyulin structuralhierarchyenhancednetworkrepresentationlearning |