2019-10-15-baloch19a.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
Focused Anchors Loss: cost-sensitive learning of discriminative features for imbalanced classification	acml19	Deep Neural Networks (DNNs) usually suffer performance penalties when there is a skewed label distribution. This phenomenon, class-imbalance, is most often mitigated peripheral to the classification algorithm itself, usually by modifying the amount of examples per class, for oversampling at the expense of computational efficiency, and for undersampling at the expense of statistical efficiency. In our solution, we combine discriminative feature learning with cost-sensitive learning to tackle the class imbalance problem by using a two step loss function, which we call the Focused Anchors loss (FAL). We evaluate FAL and its variant, Focused Anchor Mean Loss (FAML), on $6$ different datasets in comparison of traditional cross entropy loss and we observe a significant gain in balanced accuracy for all datasets. We also perform better than time-costly re-sampling and ensemble methods like SMOTE and Near Miss in $4$ out of $6$ datasets across F1-score, AUC-ROC and balanced accuracy. We also extend our evaluation to image domain and use long-tailed CIFAR$10$ to evaluate our loss function where we consistently report significant improvement in accuracy. We then go on to test our loss function under extreme imbalance on a propriety dataset and achieve a gain of $0.1$ AUC-ROC over the baseline.	inproceedings	Proceedings of Machine Learning Research	baloch19a	0	Focused Anchors Loss: cost-sensitive learning of discriminative features for imbalanced classification	822	835	822-835	822	false	Baloch, Bahram K. and Kumar, Sateesh and Haresh, Sanjay and Rehman, Abeerah and Syed, Tahir	given family Bahram K. Baloch given family Sateesh Kumar given family Sanjay Haresh given family Abeerah Rehman given family Tahir Syed	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/baloch19a/baloch19a.pdf