Abstract | ||
---|---|---|
In contrast to the standard classification paradigm where the true (or possibly noisy) class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label. This only specifies one of the classes that the pattern does not belong to. The seminal paper on complementary-label learning proposed an unbiased estimator of the classification risk that can be computed only from complementarily labeled data. However, it required a restrictive condition on the loss functions, making it impossible to use popular losses such as the softmax cross-entropy loss. Recently, another formulation with the softmax cross-entropy loss was proposed with consistency guarantee. However, this formulation does not explicitly involve a risk estimator. Thus model/hyper-parameter selection is not possible by cross-validation---we may need additional ordinarily labeled data for validation purposes, which is not available in the current setup. In this paper, we give a novel general framework of complementary-label learning, and derive an unbiased risk estimator for arbitrary losses and models. We further improve the risk estimator by non-negative correction and demonstrate its superiority through experiments. |
Year | Venue | Field |
---|---|---|
2018 | international conference on machine learning | Softmax function,Bias of an estimator,Artificial intelligence,Labeled data,Machine learning,Mathematics,Estimator |
DocType | Volume | Citations |
Journal | abs/1810.04327 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Takashi Ishida | 1 | 12 | 5.23 |
Gang Niu | 2 | 204 | 36.78 |
Aditya Krishna Menon | 3 | 709 | 40.01 |
Masashi Sugiyama | 4 | 3353 | 264.24 |