2025-01-12-jain25a.md

title	openreview	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
One-Class SVM-guided Negative Sampling for Enhanced Contrastive Learning	XCUzATsVdU	https://github.com/DJ-CHB/MiOC-Official	Recent studies on contrastive learning have emphasized carefully sampling and mixing negative samples. This study introduces a novel and improved approach for generating synthetic negatives. We propose a new method using One-Class Support Vector Machine (OCSVM) to guide in the selection process before mixing named as **Mixing OCSVM negatives (MiOC)**. Our results show that our approach creates more meaningful embeddings, which lead to better classification performance. We implement our method using publicly available datasets (Imagenet100, Cifar10, Cifar100, Cinic10, and STL10). We observed that MiOC exhibit favorable performance compared to state-of-the-art methods across these datasets. By presenting a novel approach, this study emphasizes the exploration of alternative mixing techniques that expand the sampling space beyond the conventional confines of hard negatives produced by the ranking of the dot product.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	jain25a	0	One-Class {SVM}-guided Negative Sampling for Enhanced Contrastive Learning	110	119	110-119	110	false	Jain, Dhruv and Mayet, Tsiry and H{\'E}RAULT, Romain and MODZELEWSKI, Romain	given family Dhruv Jain given family Tsiry Mayet given family Romain HÉRAULT given family Romain MODZELEWSKI	2025-01-12		Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)	265	inproceedings	date-parts 2025 1 12	https://raw.githubusercontent.com/mlresearch/v265/main/assets/jain25a/jain25a.pdf