2024-04-18-cohen-indelman24a.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
Learning Latent Partial Matchings with Gumbel-IPF Networks	https://github.com/HeddaCohenIndelman/Learning-Latent-Partial-Matchings-with-Gumbel-IPF-Networks	Learning to match discrete objects has been a central task in machine learning, often facilitated by a continuous relaxation of the matching structure. However, practical problems entail partial matchings due to missing correspondences, which pose difficulties to the one-to-one matching learning techniques that dominate the state-of-the-art. This paper introduces Gumbel-IPF networks for learning latent partial matchings. At the core of our method is the differentiable Iterative Proportional Fitting (IPF) procedure that biproportionally projects onto the transportation polytope of target marginals. Our theoretical framework also allows drawing samples from the temperature-dependent partial matching distribution. We investigate the properties of common-practice relaxations through the lens of biproportional fitting and introduce a new metric, the empirical prediction shift. Our method’s advantages are demonstrated in experimental results on the semantic keypoints partial matching task on the Pascal VOC, IMC-PT-SparseGM, and CUB2001 datasets.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	cohen-indelman24a	0	Learning Latent Partial Matchings with {G}umbel-{IPF} Networks	1513	1521	1513-1521	1513	false	Cohen Indelman, Hedda and Hazan, Tamir	given family Hedda Cohen Indelman given family Tamir Hazan	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/cohen-indelman24a/cohen-indelman24a.pdf