Presentation 2021-07-14
Relaxation of Network Restriction for Deep Learning Based Consensus Problem with Eigenvector Centrality
Shoya Ogawa, Koji Ishii,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) he convergence performance of consensus problems depends on the applied weighting factors into individual edges. Unfortunately, in the case with a complex network, the computation of optimum weighting factors is unfeasible due to high complexity. Kishida et.al., have recently proposed to apply a deep learning technique to the computation of weighting factors and shown that the deep leaning aided consensus problem can significantly enhance the convergence performance. However, since Kishida's method provides the optimum weighting factors only for the focused network topology, the calculated weighting factors cannot apply to the case with different network topology. To relax this restriction, this study proposes a learning method in which the weighting factors are computed with the constraint caused by the centrality of network. We first embed the constraint of eigenvector-centrality into the learning procedure, and the training is done with the training data which is generated with different network topology but with the same stochastic property. By doing so, the proposed method can lean the stochastic property of the network. Simulation results show that the proposed method with eigenvector centrality cannot achieve better performance than the one with degree centrality. But, both optimization can achieve better performance than the case with fixed value.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Consensus Problem / data-driven algorithm / deep-unfolding / eigenvector centrality
Paper # RCC2021-23
Date of Issue 2021-07-07 (RCC)

Conference Information
Committee RCS / SR / NS / SeMI / RCC
Conference Date 2021/7/14(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Communication and Network Technology of the AI Age, M2M (Machine-to-Machine),D2D (Device-to-Device),IoT(Internet of Things), etc
Chair Eiji Okamoto(Nagoya Inst. of Tech.) / Suguru Kameda(Hiroshima Univ.) / Akihiro Nakao(Univ. of Tokyo) / Koji Yamamoto(Kyoto Univ.) / HUAN-BANG LI(NICT)
Vice Chair Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) / Kazuto Yano(ATR) / Tetsuya Oishi(NTT) / Kazuya Monden(Hitachi) / Yasunori Owada(NICT) / Shunichi Azuma(Nagoya Univ.) / Koji Ishii(Kagawa Univ.)
Secretary Toshihiko Nishimura(NEC) / Tomoya Tandai(Panasonic) / Fumihide Kojima(Mie Univ.) / Osamu Takyu(Tokai Univ.) / Kentaro Ishidu(NTT) / Kazuto Yano(NTT) / Tetsuya Oishi(Chuo Univ.) / Kazuya Monden(Cyber Univ.) / Yasunori Owada(Waseda Univ.) / Shunichi Azuma(Osaka Univ.) / Koji Ishii(CRIEPI)
Assistant Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) / Mai Ohta(Fukuoka Univ.) / Taichi Ohtsuji(NEC) / WANG Xiaoyan(Ibaraki Univ.) / Akemi Tanaka(MathWorks) / Kotaro Mihara(NTT) / Yuki Katsumata(NTT DOCOMO) / Akihito Taya(Aoyama Gakuin Univ.) / Yu Nakayama(Tokyo Univ. of Agri. and Tech.) / SHAN LIN(NICT) / Masaki Ogura(Osaka Univ.)

Paper Information
Registration To Technical Committee on Radio Communication Systems / Technical Committee on Smart Radio / Technical Committee on Network Systems / Technical Committee on Sensor Network and Mobile Intelligence / Technical Committee on Reliable Communication and Control
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Relaxation of Network Restriction for Deep Learning Based Consensus Problem with Eigenvector Centrality
Sub Title (in English)
Keyword(1) Consensus Problem
Keyword(2) data-driven algorithm
Keyword(3) deep-unfolding
Keyword(4) eigenvector centrality
1st Author's Name Shoya Ogawa
1st Author's Affiliation Kagawa University(Kagawa Univ.)
2nd Author's Name Koji Ishii
2nd Author's Affiliation Kagawa University(Kagawa Univ.)
Date 2021-07-14
Paper # RCC2021-23
Volume (vol) vol.121
Number (no) RCC-101
Page pp.pp.7-12(RCC),
#Pages 6
Date of Issue 2021-07-07 (RCC)