| Presentation | 2021-03-05 A study of a tunable generative model for graph data using machine learning Shohei Nakazawa, Yoshiki Sato, Kenji Nakagawa, Sho Tsugawa, Kohei Watabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, applications and simulations using graphs are becoming more important. The graph has various features, and the simulation results differ depending on the features. Therefore,In recent years, applications and simulations using graphs are becoming more important. A graph has various features, and the simulation results differ depending on thefeatures. Therefore, a graph generation method for preparing a graph with various features has been studied. Classically, a model that generates using a pre-defined probability distribution of edges and nodes has been studied. In recent years, a method of generating a graph that imitates the learned graph by learning features from actual graph data using machine learning has been studied. However, in conventional research using machine learning, features can be learned from data, but it is not possible to specify features and generate graphs of arbitrary features. In this paper, we propose a model that learns graphs from data and can generate a specified graph by specifying a value of a feature. With the proposed model that learned graphs of various features generated by the conventional method, we verified whether the graphs of arbitrary features could be generated by specifying the features. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | network / graph / generate / conditional VAE / machine learning |
| Paper # | NS2020-159 |
| Date of Issue | 2021-02-25 (NS) |
| Conference Information | |
| Committee | IN / NS |
|---|---|
| Conference Date | 2021/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General |
| Chair | Kenji Ishida(Hiroshima City Univ.) / Akihiro Nakao(Univ. of Tokyo) |
| Vice Chair | Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT) |
| Secretary | Kunio Hato(Hiroshima City Univ.) / Tetsuya Oishi(KDDI Research) |
| Assistant | / Shinya Kawano(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Network Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A study of a tunable generative model for graph data using machine learning |
| Sub Title (in English) | |
| Keyword(1) | network |
| Keyword(2) | graph |
| Keyword(3) | generate |
| Keyword(4) | conditional VAE |
| Keyword(5) | machine learning |
| 1st Author's Name | Shohei Nakazawa |
| 1st Author's Affiliation | Nagaoka University of Technology(Nagaoka Univ. of Tech.) |
| 2nd Author's Name | Yoshiki Sato |
| 2nd Author's Affiliation | Nagaoka University of Technology(Nagaoka Univ. of Tech.) |
| 3rd Author's Name | Kenji Nakagawa |
| 3rd Author's Affiliation | Nagaoka University of Technology(Nagaoka Univ. of Tech.) |
| 4th Author's Name | Sho Tsugawa |
| 4th Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
| 5th Author's Name | Kohei Watabe |
| 5th Author's Affiliation | Nagaoka University of Technology(Nagaoka Univ. of Tech.) |
| Date | 2021-03-05 |
| Paper # | NS2020-159 |
| Volume (vol) | vol.120 |
| Number (no) | NS-413 |
| Page | pp.pp.214-219(NS), |
| #Pages | 6 |
| Date of Issue | 2021-02-25 (NS) |