Timezone: »

 
Poster
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
Yivan Zhang · Gang Niu · Masashi Sugiyama

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @ Virtual #None

Many weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks. In this work, we propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously, without relying on the error-prone noisy class-posterior estimation. Concretely, inspired by the characteristics of the stochastic label corruption process, we propose total variation regularization, which encourages the predicted probabilities to be more distinguishable from each other. Under mild assumptions, the proposed method yields a consistent estimator of the transition matrix. We show the effectiveness of the proposed method through experiments on benchmark and real-world datasets.

Author Information

Yivan Zhang (The University of Tokyo / RIKEN)
Gang Niu (RIKEN)
Gang Niu

Gang Niu is currently an indefinite-term research scientist at RIKEN Center for Advanced Intelligence Project.

Masashi Sugiyama (RIKEN / The University of Tokyo)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors