Ranking-preserved generative label enhancement

Label distribution learning (LDL) is effective for addressing label ambiguity. In LDL, ground-truth label distributions are hardly available due to the high annotation cost, whereas it is relatively easy to obtain examples with logical labels. Hence, label enhancement (LE) is proposed to automatically transform logical labels into label distributions. Most existing LE methods employ discriminative approaches. However, discriminative approaches specialize in obtaining better predictive performance under supervised learning, and their capability is limited in LE that lacks supervisory information. Therefore, we propose a generative LE model, and infer label distributions by the variational Bayes capable of preserving the label ranking within the logical label vector. Our method consists of a generation process and an inference process. In the generation process, we treat label distributions as latent variables, and assume that label distributions generate logical labels and feature values of the instance itself and logical labels of the neighbors of this instance. In the inference process, we design a function, which mines the label correlation and preserves the label ranking within the logical label vector, to parameterize the variational posterior. Finally, we conduct extensive experiments to validate our proposal.

Automated summary

Label distribution learning (LDL) addresses label ambiguity by transforming logical labels into label distributions. We propose a generative label enhancement model that utilizes variational Bayes inference to infer label distributions while preserving label ranking and correlation. Extensive experiments validate the effectiveness of our method.