@conference{Perez2019Exploiting,
author = "Mar{\'i}a P{\'e}rez-Ortiz and Peter Tino and Rafal Mantiuk and C{\'e}sar Herv{\'a}s-Mart{\'i}nez",
abstract = "Data  augmentation  is  rapidly  gaining  attention  in  machinelearning. Synthetic data can be generated by simple transfor-mations  or  through  the  data  distribution.  In  the  latter  case,the main challenge is to estimate the label associated to newsynthetic patterns. This paper studies the effect of generat-ing synthetic data by convex combination of patterns and theuse of these as unsupervised information in a semi-supervisedlearning framework with support vector machines, avoidingthus  the  need  to  label  synthetic  examples.  We  perform  ex-periments on a total of 53 binary classification datasets. Ourresults  show  that  this  type  of  data  over-sampling  supportsthe well-known cluster assumption in semi-supervised learn-ing, showing outstanding results for small high-dimensionaldatasets and imbalanced learning problems.",
booktitle = "Proceedings of the Thirty-Third AAAI (Association for the Advancement of  Artificial Intelligence) Conference on Artificial Intelligence (AAAI'19)",
doi = "10.1609/aaai.v33i01.33014715",
isbn = "978-1-57735-809-1",
issn = "2159-5399",
month = "27th February",
organization = "Honolulu,Hawaii, USA",
pages = "4715-4722",
title = "{E}xploiting synthetically generated data with semi-supervised learning for small and imbalanced datasets",
url = "doi.org/10.1609/aaai.v33i01.33014715",
year = "2019",
}