2024-04-18-demetci24a.md

title	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
Breaking isometric ties and introducing priors in Gromov-Wasserstein distances	https://github.com/pinardemetci/AGW-AISTATS24	Gromov-Wasserstein distance has many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariant property can be too flexible, thus undesirable. Moreover, the Gromov-Wasserstein distance solely considers pairwise sample similarities in input datasets, disregarding the raw feature representations. We propose a new optimal transport formulation, called Augmented Gromov-Wasserstein (AGW), that allows for some control over the level of rigidity to transformations. It also incorporates feature alignments, enabling us to better leverage prior knowledge on the input data for improved performance. We first present theoretical insights into the proposed method. We then demonstrate its usefulness for single-cell multi-omic alignment tasks and heterogeneous domain adaptation in machine learning.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	demetci24a	0	Breaking isometric ties and introducing priors in {G}romov-{W}asserstein distances	298	306	298-306	298	false	Demetci, Pinar and Huy Tran, Quang and Redko, Ievgen and Singh, Ritambhara	given family Pinar Demetci given family Quang Huy Tran given family Ievgen Redko given family Ritambhara Singh	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/demetci24a/demetci24a.pdf