Learning feature representation for subgraphs
Graphs are a rich and versatile data structure. They are widely used in representing data like social networks, chemical compound, protein structures. Analytical tasks against graph data attracted great attention in many domains. Effective graph analytics provides users deep insights of the data. Ho...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/75535 |
| _version_ | 1826113129962012672 |
|---|---|
| author | Zhang, Linghan |
| author2 | Chen Lihui |
| author_facet | Chen Lihui Zhang, Linghan |
| author_sort | Zhang, Linghan |
| collection | NTU |
| description | Graphs are a rich and versatile data structure. They are widely used in representing data like social networks, chemical compound, protein structures. Analytical tasks against graph data attracted great attention in many domains. Effective graph analytics provides users deep insights of the data. However, due to the structural characteristics of graphs, computation cost for graph analytics tasks on large graph data set can be very high. We discuss two recent frameworks inspired by the advancements in feature representation learning, neural networks and graph kernels, namely patchy-san and subgraph2vec. We conducted experiments with patchy-san and subgraph2vec frameworks for graph classification problems. With established benchmark datasets, we demonstrate that these two frameworks, despite taking different approaches, are efficient and competitive with state-of-the-art techniques. |
| first_indexed | 2024-10-01T03:18:28Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/75535 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:18:28Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/755352023-07-07T16:18:16Z Learning feature representation for subgraphs Zhang, Linghan Chen Lihui School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering Graphs are a rich and versatile data structure. They are widely used in representing data like social networks, chemical compound, protein structures. Analytical tasks against graph data attracted great attention in many domains. Effective graph analytics provides users deep insights of the data. However, due to the structural characteristics of graphs, computation cost for graph analytics tasks on large graph data set can be very high. We discuss two recent frameworks inspired by the advancements in feature representation learning, neural networks and graph kernels, namely patchy-san and subgraph2vec. We conducted experiments with patchy-san and subgraph2vec frameworks for graph classification problems. With established benchmark datasets, we demonstrate that these two frameworks, despite taking different approaches, are efficient and competitive with state-of-the-art techniques. Bachelor of Engineering 2018-06-01T05:50:50Z 2018-06-01T05:50:50Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/75535 en Nanyang Technological University 55 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Zhang, Linghan Learning feature representation for subgraphs |
| title | Learning feature representation for subgraphs |
| title_full | Learning feature representation for subgraphs |
| title_fullStr | Learning feature representation for subgraphs |
| title_full_unstemmed | Learning feature representation for subgraphs |
| title_short | Learning feature representation for subgraphs |
| title_sort | learning feature representation for subgraphs |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | http://hdl.handle.net/10356/75535 |
| work_keys_str_mv | AT zhanglinghan learningfeaturerepresentationforsubgraphs |