Timezone: »

SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Haobo Wang · Mingxuan Xia · Yixuan Li · Yuren Mao · Lei Feng · Gang Chen · Junbo Zhao


Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior work failed. We subsequently propose SoLar, a novel Optimal Transport-based framework that allows to refine the disambiguated labels towards matching the marginal class prior distribution. SoLar additionally incorporates a new and systematic mechanism for estimating the long-tailed class prior distribution under the PLL setup. Through extensive experiments, SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-of-the-art PLL methods.

Author Information

Haobo Wang (Zhejiang University)
Mingxuan Xia (Zhejiang University)
Yixuan Li (University of Wisconsin-Madison)
Yuren Mao (Zhejiang University)

Yuren Mao received his PhD degree in computer science from University of New South Wales, Australia in 2022. He is currently an assistant professor with the School of Software Technology, Zhejiang University, China. His current research interests include Multi-task Learning and its applications. His research results have been published at leading conferences such as ICML, NeurIPS, ACL, TKDE and so on.

Lei Feng (Nanyang Technological University, Singapore)
Gang Chen (College of Computer Science and Technology, Zhejiang University)
Junbo Zhao (Zhejiang University)

More from the Same Authors