This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta classification learning, optimizes a binary classifier for pairwise similarity prediction and through this process learns a multi-class classifier as a submodule. We formulate this approach, present a probabilistic graphical model for it, and derive a surprisingly simple loss function that can be used to learn neural network-based models. We then demonstrate that this same framework generalizes to the supervised, unsupervised cross-task, and semi-supervised settings. Our method is evaluated against state of the art in all three learning paradigms and shows a superior or comparable accuracy, providing evidence that learning multi-class classification without multi-class labels is a viable learning option.

论文提出了一种基于对比相似度而非类别标签的多类分类策略, 称之为元分类学习, 通过优化二元分类器以预测对比相似度从而实现多类分类，提出了概率图模型并衍生出一个简单的损失函数，用于学习基于神经网络的模型，并在监督、非监督跨任务和半监督设置下均取得了明显优于或与最先进方法相当的准确性。

无需多类标签的多类分类