Representation learning on heterogenous information networks
In real world, most of the information networks are heterogeneous in nature, which contains different types of nodes and relationships. Representation learning or feature learning techniques are needed to extract features of these Heterogeneous Information Networks (HIN) and convert them to low dime...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/150188 |
| _version_ | 1811679013450547200 |
|---|---|
| author | Chen, Xiaoyu |
| author2 | Lihui CHEN |
| author_facet | Lihui CHEN Chen, Xiaoyu |
| author_sort | Chen, Xiaoyu |
| collection | NTU |
| description | In real world, most of the information networks are heterogeneous in nature, which contains different types of nodes and relationships. Representation learning or feature learning techniques are needed to extract features of these Heterogeneous Information Networks (HIN) and convert them to low dimensional vectors such that they can be used as input to machine learning models to perform machine learning tasks. Current graph embedding methods have the limitations on either considering singular types of nodes and relationships or losing important node features due to ignoring node contents or relationships between nodes. In this project, an advanced graph embedding technique, Metapath Aggregated Graph Neural Network (MAGNN), is studied. With the idea of metapath, which captures the relationships between node types, and graph neural network, a powerful graph embedding model based on deep learning, MAGNN aims to address these problems and generate node embedding with more structural and semantic information of HIN. Empirical studies with more benchmark datasets are conducted to investigate the effectiveness of MAGNN model. The results are useful for comparison with the state-of-the art baselines. |
| first_indexed | 2024-10-01T03:02:24Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/150188 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:02:24Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1501882023-07-07T18:17:12Z Representation learning on heterogenous information networks Chen, Xiaoyu Lihui CHEN School of Electrical and Electronic Engineering ELHCHEN@ntu.edu.sg Engineering::Electrical and electronic engineering In real world, most of the information networks are heterogeneous in nature, which contains different types of nodes and relationships. Representation learning or feature learning techniques are needed to extract features of these Heterogeneous Information Networks (HIN) and convert them to low dimensional vectors such that they can be used as input to machine learning models to perform machine learning tasks. Current graph embedding methods have the limitations on either considering singular types of nodes and relationships or losing important node features due to ignoring node contents or relationships between nodes. In this project, an advanced graph embedding technique, Metapath Aggregated Graph Neural Network (MAGNN), is studied. With the idea of metapath, which captures the relationships between node types, and graph neural network, a powerful graph embedding model based on deep learning, MAGNN aims to address these problems and generate node embedding with more structural and semantic information of HIN. Empirical studies with more benchmark datasets are conducted to investigate the effectiveness of MAGNN model. The results are useful for comparison with the state-of-the art baselines. Bachelor of Engineering (Electrical and Electronic Engineering) 2021-06-12T13:26:06Z 2021-06-12T13:26:06Z 2021 Final Year Project (FYP) Chen, X. (2021). Representation learning on heterogenous information networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/150188 https://hdl.handle.net/10356/150188 en A3048-201 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Chen, Xiaoyu Representation learning on heterogenous information networks |
| title | Representation learning on heterogenous information networks |
| title_full | Representation learning on heterogenous information networks |
| title_fullStr | Representation learning on heterogenous information networks |
| title_full_unstemmed | Representation learning on heterogenous information networks |
| title_short | Representation learning on heterogenous information networks |
| title_sort | representation learning on heterogenous information networks |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/150188 |
| work_keys_str_mv | AT chenxiaoyu representationlearningonheterogenousinformationnetworks |