| Presentation | 2018-08-09 Derivation and Experimental Evaluation of a Novel Nonnegative Matrix Factorization Algorithm for Discovering Communities Yoshito Usuzaka, Norikazu Takahashi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Community discovery is an important technique for a better understanding of the structure of a network. We consider the community discovery for a given directed network as the problem of partitioning the vertex set into some subsets, i.e., communities, such that two distinct subsets are connected by directed edges with a much higher density than average, or a much lower density than average. It is known that this can be formulated as a nonnegative matrix factorization problem. Also, an iterative algorithm for solving the problem has been developed. In this report, we derive a novel iterative algorithm for solving the same problem, and experimentally evaluate the convergence rate and the capability of discovering communities. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | directed network / community discovery / nonnegative matrix factorization / Cardano's method |
| Paper # | NLP2018-64 |
| Date of Issue | 2018-08-01 (NLP) |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2018/8/8(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Saiwai-cho Campus, Kagawa Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | etc. |
| Chair | Norikazu Takahashi(Okayama Univ.) |
| Vice Chair | Hiroaki Kurokawa(Tokyo Univ. of Tech.) |
| Secretary | Hiroaki Kurokawa(Hiroshima Inst. of Tech.) |
| Assistant | Masayuki Kimura(Kyoto Univ.) / Yutaka Shimada(Saitama Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Derivation and Experimental Evaluation of a Novel Nonnegative Matrix Factorization Algorithm for Discovering Communities |
| Sub Title (in English) | |
| Keyword(1) | directed network |
| Keyword(2) | community discovery |
| Keyword(3) | nonnegative matrix factorization |
| Keyword(4) | Cardano's method |
| 1st Author's Name | Yoshito Usuzaka |
| 1st Author's Affiliation | Okayama University(Okayama Univ.) |
| 2nd Author's Name | Norikazu Takahashi |
| 2nd Author's Affiliation | Okayama University(Okayama Univ.) |
| Date | 2018-08-09 |
| Paper # | NLP2018-64 |
| Volume (vol) | vol.118 |
| Number (no) | NLP-174 |
| Page | pp.pp.57-62(NLP), |
| #Pages | 6 |
| Date of Issue | 2018-08-01 (NLP) |