In this paper, we study dataset distillation (DD), from a novel perspective and introduce a\emph {dataset factorization} approach, termed\emph {HaBa}, which is a plug-and-play …
S Liu, J Ye, R Yu, X Wang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Dataset distillation, also known as dataset condensation, aims to compress a large dataset into a compact synthetic one. Existing methods perform dataset condensation by assuming a …
Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets …
Y Wu, Z Chi, Y Wang, S Feng - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes …
C Chen, J Zhou, F Wang, X Liu, D Dou - Bioinformatics, 2023 - academic.oup.com
Motivation Protein representation learning methods have shown great potential to many downstream tasks in biological applications. A few recent studies have demonstrated that …
T Zhong, Z Chi, L Gu, Y Wang… - Advances in Neural …, 2022 - proceedings.neurips.cc
In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all …
Experimental design is a fundamental problem in many science and engineering fields. In this problem, sample efficiency is crucial due to the time, money, and safety costs of real …
Y Yuan, CS Chen, Z Liu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design …
CS Chen, C Beckham, Z Liu… - Advances in Neural …, 2024 - proceedings.neurips.cc
We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores. These designs encompass a variety of domains …