期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 31, 期 7, 页码 2315-2324出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2019.2935143
关键词
Predictive models; Measurement; Training; Prediction algorithms; Correlation; Sparse matrices; Learning systems; Large-scale multi-label learning (LMLL); performance metric; scalability; tail label
类别
资金
- National Key RAMP
- D Program of China [2017YFB1002201]
- National Natural Science Foundation of China [61772262]
- Fundamental Research Funds for the Central Universities [020214380053]
Large-scale multi-label learning (LMLL) annotates relevant labels for unseen data from a huge number of candidate labels. It is perceived that labels exhibit a long tail distribution in which a significant number of labels are tail labels. Most previous studies consider that the performance would benefit from incorporating tail labels. Nonetheless, it is not quantified how tail labels impact the performance. In this article, we disclose that whatever labels are randomly missing or misclassified, the impact of labels on commonly used LMLL evaluation metrics (Propensity Score Precision (PSP)@k and Propensity Score nDCG (PSnDCG)@k) is directly related to the product of the label weights and the label frequencies. In particular, when labels share equal weights, tail labels impact much less than common labels due to the scarcity of relevant examples. Based on such observation, we propose to develop low-complexity LMLL methods with the goal of facilitating fast prediction time and compact model size by restraining less performance-influential labels. With the consideration that discarding labels may cause the loss of predictive capability, we further propose to preserve dominant model parameters for the less performance-influential labels. Experiments clearly justify that both the prediction time and the model size are significantly reduced without sacrificing much predictive performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据