2019-10-15-mollaysa19a.md

title	crossref	abstract	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
Learning to Augment with Feature Side-information	acml19	Neural networks typically need huge amounts of data to train in order to get reasonable generalizable results. A common approach is to artificially generate samples by using prior knowledge of the data properties or other relevant domain knowledge. However, if the assumptions on the data properties are not accurate or the domain knowledge is irrelevant to the task at hand, one may end up degenerating learning performance by using such augmented data in comparison to simply training on the limited available dataset. We propose a critical data augmentation method using feature side-information, which is obtained from domain knowledge and provides detailed information about features' intrinsic properties. Most importantly, we introduce an instance wise quality checking procedure on the augmented data. It filters out irrelevant or harmful augmented data prior to entering the model. We validated this approach on both synthetic and real-world datasets, specifically in a scenario where the data augmentation is done based on a task independent, unreliable source of information. The experiments show that the introduced critical data augmentation scheme helps avoid performance degeneration resulting from incorporating wrong augmented data.	inproceedings	Proceedings of Machine Learning Research	mollaysa19a	0	Learning to Augment with Feature Side-information	173	187	173-187	173	false	Mollaysa, Amina and Kalousis, Alexandros and Bruno, Eric and Diephuis, Maurits	given family Amina Mollaysa given family Alexandros Kalousis given family Eric Bruno given family Maurits Diephuis	2019-10-15		PMLR	Proceedings of The Eleventh Asian Conference on Machine Learning	101	inproceedings	date-parts 2019 10 15	http://proceedings.mlr.press/v101/mollaysa19a/mollaysa19a.pdf