Affinity Learning on Graphs with Diffusion Processes
In the thesis, we propose machine learning algorithms utilising diffusion processes to learn the pairwise affinity between data samples. Diffusion processes propagates neighbour information on a node-edge graph, resulting in context-aware affinities that is smooth to the data manifold structure. Sim...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2020
|
| Online Access: | http://hdl.handle.net/20.500.11937/80408 |
| _version_ | 1848764213712912384 |
|---|---|
| author | Li, Qilin |
| author_facet | Li, Qilin |
| author_sort | Li, Qilin |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In the thesis, we propose machine learning algorithms utilising diffusion processes to learn the pairwise affinity between data samples. Diffusion processes propagates neighbour information on a node-edge graph, resulting in context-aware affinities that is smooth to the data manifold structure. Similar ideas are also embedded in graph convolutional networks for representation learning. These proposed algorithms improve performance for various machine learning tasks, such as data cluster analysis, dimensionality reduction, and semisupervised classification. |
| first_indexed | 2025-11-14T11:15:47Z |
| format | Thesis |
| id | curtin-20.500.11937-80408 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:15:47Z |
| publishDate | 2020 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-804082022-08-05T04:34:34Z Affinity Learning on Graphs with Diffusion Processes Li, Qilin In the thesis, we propose machine learning algorithms utilising diffusion processes to learn the pairwise affinity between data samples. Diffusion processes propagates neighbour information on a node-edge graph, resulting in context-aware affinities that is smooth to the data manifold structure. Similar ideas are also embedded in graph convolutional networks for representation learning. These proposed algorithms improve performance for various machine learning tasks, such as data cluster analysis, dimensionality reduction, and semisupervised classification. 2020 Thesis http://hdl.handle.net/20.500.11937/80408 Curtin University fulltext |
| spellingShingle | Li, Qilin Affinity Learning on Graphs with Diffusion Processes |
| title | Affinity Learning on Graphs with Diffusion Processes |
| title_full | Affinity Learning on Graphs with Diffusion Processes |
| title_fullStr | Affinity Learning on Graphs with Diffusion Processes |
| title_full_unstemmed | Affinity Learning on Graphs with Diffusion Processes |
| title_short | Affinity Learning on Graphs with Diffusion Processes |
| title_sort | affinity learning on graphs with diffusion processes |
| url | http://hdl.handle.net/20.500.11937/80408 |