2024-04-18-braun24b.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
Deep Classifier Mimicry without Data Access	https://github.com/ml-research/CAKE	Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may not equally be granted. This makes it tremendously challenging to fine-tune, compress models, adapt continually, or to do any other type of data-driven update. We posit that original data access may however not be required. Specifically, we propose Contrastive Abductive Knowledge Extraction (CAKE), a model-agnostic knowledge distillation procedure that mimics deep classifiers without access to the original data. To this end, CAKE generates pairs of noisy synthetic samples and diffuses them contrastively toward a model’s decision boundary. We empirically corroborate CAKE’s effectiveness using several benchmark datasets and various architectural choices, paving the way for broad application.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	braun24b	0	Deep Classifier Mimicry without Data Access	4762	4770	4762-4770	4762	false	Braun, Steven and Mundt, Martin and Kersting, Kristian	given family Steven Braun given family Martin Mundt given family Kristian Kersting	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/braun24b/braun24b.pdf