Skip to Main content Skip to Navigation
Conference papers

Learning from Networked Examples

Yuyi Wang 1 Zheng-Chu Guo 2 Jan Ramon 3
3 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may share some common objects, and hence share the features of these shared objects. We show that the classic approach of ignoring this problem potentially can have a harmful effect on the accuracy of statistics, and then consider alternatives. One of these is to only use independent examples, discarding other information. However, this is clearly suboptimal. We analyze sample error bounds in this networked setting, providing significantly improved results. An important component of our approach is formed by efficient sample weighting schemes, which leads to novel concentration inequalities.
Complete list of metadata

Cited literature [34 references]  Display  Hide  Download
Contributor : Jan Ramon Connect in order to contact the contributor
Submitted on : Wednesday, March 25, 2020 - 8:33:10 PM
Last modification on : Friday, January 21, 2022 - 3:13:14 AM


Files produced by the author(s)


  • HAL Id : hal-02519274, version 1


Yuyi Wang, Zheng-Chu Guo, Jan Ramon. Learning from Networked Examples. ALT 2017 - 28th conference on Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1 - 26. ⟨hal-02519274⟩



Les métriques sont temporairement indisponibles