Timezone: »

Pointwise Binary Classification with Pairwise Confidence Comparisons
Lei Feng · Senlin Shu · Nan Lu · Bo Han · Miao Xu · Gang Niu · Bo An · Masashi Sugiyama

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @

To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed. Among them, some consider using pairwise but not pointwise labels, when pointwise labels are not accessible due to privacy, confidentiality, or security reasons. However, as a pairwise label denotes whether or not two data points share a pointwise label, it cannot be easily collected if either point is equally likely to be positive or negative. Thus, in this paper, we propose a novel setting called pairwise comparison (Pcomp) classification, where we have only pairs of unlabeled data that we know one is more likely to be positive than the other. Firstly, we give a Pcomp data generation process, derive an unbiased risk estimator (URE) with theoretical guarantee, and further improve URE using correction functions. Secondly, we link Pcomp classification to noisy-label learning to develop a progressive URE and improve it by imposing consistency regularization. Finally, we demonstrate by experiments the effectiveness of our methods, which suggests Pcomp is a valuable and practically useful type of pairwise supervision besides the pairwise label.

Author Information

Lei Feng (College of Computer Science, Chongqing University)
Senlin Shu (Southwest University, Chongqing, China)
Nan Lu (The University of Tokyo/RIKEN)

Nan Lu is a Ph.D. student at the Department of Complexity Science and Engineering, the University of Tokyo. Her research interests lie in the fields of weakly supervised learning, learning with real-world constraints, and deep learning.

Miao Xu (University of Queensland)
Gang Niu (RIKEN)
Gang Niu

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

Bo An (Nanyang Technological University)
Masashi Sugiyama (RIKEN / The University of Tokyo)

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

More from the Same Authors