Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation

by   Wei-I Lin, et al.
National Taiwan University
The University of Tokyo

Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies typically use novel loss functions or training techniques to solve this problem, few studies focus on how complementary labels collectively provide information to train the ordinary classifier. In this paper, we fill the gap by analyzing the implicit sharing of complementary labels on nearby instances during training. Our analysis reveals that the efficiency of implicit label sharing is closely related to the performance of existing CLL models. Based on this analysis, we propose a novel technique that enhances the sharing efficiency via complementary-label augmentation, which explicitly propagates additional complementary labels to each instance. We carefully design the augmentation process to enrich the data with new and accurate complementary labels, which provide CLL models with fresh and valuable information to enhance the sharing efficiency. We then verify our proposed technique by conducting thorough experiments on both synthetic and real-world datasets. Our results confirm that complementary-label augmentation can systematically improve empirical performance over state-of-the-art CLL models.


page 1

page 2

page 3

page 4


Bridging Ordinary-Label Learning and Complementary-Label Learning

Unlike ordinary supervised pattern recognition, in a newly proposed fram...

CLCIFAR: CIFAR-Derived Benchmark Datasets with Human Annotated Complementary Labels

As a weakly-supervised learning paradigm, complementary label learning (...

Reduction from Complementary-Label Learning to Probability Estimates

Complementary-Label Learning (CLL) is a weakly-supervised learning probl...

Generative-Discriminative Complementary Learning

Majority of state-of-the-art deep learning methods for vision applicatio...

Learning from Complementary Labels

Collecting labeled data is costly and thus a critical bottleneck in real...

Learning with Biased Complementary Labels

In this paper we study the classification problem in which we have acces...

Mitigating Label Noise through Data Ambiguation

Label noise poses an important challenge in machine learning, especially...

Please sign up or login with your details

Forgot password? Click here to reset