Privacy-preserving graph representation learning
Among the various machine learning algorithms created to handle data with underlying graph structures are graph neural networks. There are several disciplines in which graph representation learning is used. Graph neural networks in particular, as a novel kind of link prediction method, can extract h...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/178703 |
| _version_ | 1824455658927292416 |
|---|---|
| author | Lan, Xin |
| author2 | Tay Wee Peng |
| author_facet | Tay Wee Peng Lan, Xin |
| author_sort | Lan, Xin |
| collection | NTU |
| description | Among the various machine learning algorithms created to handle data with underlying graph structures are graph neural networks. There are several disciplines in which graph representation learning is used. Graph neural networks in particular, as a novel kind of link prediction method, can extract hidden link information from accessible network data in the field of link prediction. However, certain edges or connections between network nodes that are sensitive may be exposed by the learnt graph representation.
In this dissertation, we investigate techniques for graph representation learning that safeguard connections’ privacy. We achieve privacy protection with link prediction in two ways. The first aspect is to view the privacy preservation problem as an optimization problem. Through optimization iterations we can achieve effective privacy preservation. The second aspect is to introduce a graph attack strategy, which attacks the target graph against the graph neural network algorithm in order to reduce the accuracy of the link prediction of the graph neural network, so that a certain degree of privacy protection can be realized. |
| first_indexed | 2025-02-19T03:41:43Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/178703 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:41:43Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1787032024-07-05T15:43:10Z Privacy-preserving graph representation learning Lan, Xin Tay Wee Peng School of Electrical and Electronic Engineering wptay@ntu.edu.sg Computer and Information Science Engineering Among the various machine learning algorithms created to handle data with underlying graph structures are graph neural networks. There are several disciplines in which graph representation learning is used. Graph neural networks in particular, as a novel kind of link prediction method, can extract hidden link information from accessible network data in the field of link prediction. However, certain edges or connections between network nodes that are sensitive may be exposed by the learnt graph representation. In this dissertation, we investigate techniques for graph representation learning that safeguard connections’ privacy. We achieve privacy protection with link prediction in two ways. The first aspect is to view the privacy preservation problem as an optimization problem. Through optimization iterations we can achieve effective privacy preservation. The second aspect is to introduce a graph attack strategy, which attacks the target graph against the graph neural network algorithm in order to reduce the accuracy of the link prediction of the graph neural network, so that a certain degree of privacy protection can be realized. Master's degree 2024-07-03T00:53:15Z 2024-07-03T00:53:15Z 2024 Thesis-Master by Coursework Lan, X. (2024). Privacy-preserving graph representation learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/178703 https://hdl.handle.net/10356/178703 en application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Engineering Lan, Xin Privacy-preserving graph representation learning |
| title | Privacy-preserving graph representation learning |
| title_full | Privacy-preserving graph representation learning |
| title_fullStr | Privacy-preserving graph representation learning |
| title_full_unstemmed | Privacy-preserving graph representation learning |
| title_short | Privacy-preserving graph representation learning |
| title_sort | privacy preserving graph representation learning |
| topic | Computer and Information Science Engineering |
| url | https://hdl.handle.net/10356/178703 |
| work_keys_str_mv | AT lanxin privacypreservinggraphrepresentationlearning |