System Development & Application
|
App. Res. of Comp. Printed Article
Vol. 38, 2021 No. 2
510-516,521

Tuning method of hyper-parameters for SGNS algorithm based on robust design

Niu Qian
Cao Xuefei
Wang Ruibo
Li Jihong
School of Software, Shanxi University, Taiyuan 030006, China
DOI: 10.19734/j.issn.1001-3695.2019.12.0672

Abstract

Usually, the tuning method used commonly is to select the optimal combination of the values with the largest performance measure(called direct tuning method). However, this method has poor robustness. Hence, this paper proposed a robust hyper-parameter tuning method. Specifically, taking the tuning of SGNS(skip-gram with negative-sample) algorithm as an example in word analogy task, it drew the conclusions as follow. Five of all seven hyper-parameters in SGNS that had significant influence on the performance were determined as the control factors and remained two as the noise factors, and three of the five control factors had significant influence on the variance of the performance measure after ANOVA for experimental data. Therefore, direct selection the optimal combination only by maximum expectation was not reasonable. There was no significant difference in the prediction accuracy between robust tuning method and direct tuning method, but robust tuning method remarkably had good robustness. The robust tuning method had practical referential value for tuning hyper-parameters of deep neural networks.

Foundation Support

国家自然科学基金青年基金资助项目(61806115,61603228)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2019.12.0672
Publish at: Application Research of Computers Printed Article, Vol. 38, 2021 No. 2
Section: System Development & Application
Pages: 510-516,521
Serial Number: 1001-3695(2021)02-036-0510-07

Publish History

[2021-02-05] Printed Article

Cite This Article

牛倩, 曹学飞, 王瑞波, 等. 基于稳健设计的SGNS算法的超参数调优方法 [J]. 计算机应用研究, 2021, 38 (2): 510-516,521. (Niu Qian, Cao Xuefei, Wang Ruibo, et al. Tuning method of hyper-parameters for SGNS algorithm based on robust design [J]. Application Research of Computers, 2021, 38 (2): 510-516,521. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)