The Selected-completely-at-random Complementary Label is a Practical Weak Supervision for Multi-class Classification

arXiv:2311.15502v2 Announce Type: replace
Abstract: Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases. However, either condition may not be satisfied in real-world scenarios. In this paper, we …

abstract arxiv class classification consistent cs.lg distribution example labels multiple practical random supervised learning supervision training type uniform