Timezone: »

Progressive Identification of True Labels for Partial-Label Learning
Jiaqi Lv · Miao Xu · LEI FENG · Gang Niu · Xin Geng · Masashi Sugiyama

Thu Jul 16 08:00 AM -- 08:45 AM & Thu Jul 16 07:00 PM -- 07:45 PM (PDT) @ None #None

Partial-label learning is one of the important weakly supervised learning problems, where each training example is equipped with a set of candidate labels that contains the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of partial-label learning without implicit assumptions on the model or optimization algorithm. More specifically, we propose a general estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. We then explore a progressive identification method for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels can be conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.

Author Information

Jiaqi Lv (Southeast University)
Miao Xu (University of Queensland/ RIKEN AIP)
LEI FENG (Nanyang Technological University)
Gang Niu (RIKEN)
Xin Geng (Southeast University)
Masashi Sugiyama (RIKEN / The University of Tokyo)

More from the Same Authors