Timezone: »

Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?
Yu Yao · Mingming Gong · Yuxuan Du · Jun Yu · Bo Han · Kun Zhang · Tongliang Liu

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #416

In real life, accurately annotating large-scale datasets is sometimes difficult. Datasets used for training deep learning models are likely to contain label noise. To make use of the dataset containing label noise, two typical methods have been proposed. One is to employ the semi-supervised method by exploiting labeled confident examples and unlabeled unconfident examples. The other one is to model label noise and design statistically consistent classifiers. A natural question remains unsolved: which one should be used for a specific real-world application? In this paper, we answer the question from the perspective of causal data generative process. Specifically, the performance of the semi-supervised based method depends heavily on the data generative process while the method modeling label-noise is not influenced by the generation process. For example, for a given dataset, if it has a causal generative structure that the features cause the label, the semi-supervised based method would not be helpful. When the causal structure is unknown, we provide an intuitive method to discover the causal structure for a given dataset containing label noise.

Author Information

Yu Yao (University of Sydney)
Mingming Gong (University of Melbourne)
Yuxuan Du (JD Explore Academy)
Jun Yu (University of Science and Technology of China)
Kun Zhang (Carnegie Mellon University)
Tongliang Liu (The University of Sydney)

More from the Same Authors