Earticle

초록

영어

Relational classification (RC) is concerned with the application of statistical learning to relational data. RC models do not have improved stability to smooth the perturbations generated by variations in the correlation between the relational data. Therefore, few studies have attempted to derive a bound and develop a stability learning framework for RC models. To solve this problem, we derive a learning bound with a new measure dependence stability and a limited Vapnik–Chervonenkis (VC) dimension. Based on the learning bound, we then design a stable learning framework that serves as a guideline for the development of new learning algorithms for a broad class of RC models. Applying a Markov logic network on synthesized and real-world datasets, our experimental results demonstrate that our bound can be tight if the RC model has appropriate dependence stability and limited VC dimension and our learning framework increases the stability of RC models while reducing the deviation between empirical risk and true risk.

목차

Abstract
 1. Introduction
 2. Preliminaries
  2.1. Set up
  2.2. Dependence Measures
  2.3. Calculation of the Dependence Measures
 3. Dependence Stability of RC Models
 4. Generalization Bounds
  4.1. Concentration Inequality
  4.2. Dependence Stability Learning Bounds
 5. Stable Learning Framework
  5.1. Feasibility Analysis
  5.2. Learning Framework Design
 6. Experiments
  6.1. Synthetic and Real Datasets
  6.2. Dependence Stability Learning
 7. Conclusion
 8. Appendex
 References

키워드

저자

• Xing Wang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Hui He [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Bin-Xing Fang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]
• Hong-Li Zhang [ Department of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, P.R.China, 150001 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605