Concentration Distribution Learning from Label Distributions
This work addresses a limitation in label distribution learning for machine learning applications, offering an incremental improvement by enhancing representation completeness.
The paper tackles the problem of label distribution learning (LDL) by introducing a new concept called background concentration to represent absolute label intensities, addressing information loss from hidden labels. The proposed concentration distribution learning approach, implemented with probabilistic methods and neural networks, achieves more accurate predictions than state-of-the-art LDL methods in experiments.
Label distribution learning (LDL) is an effective method to predict the relative label description degree (a.k.a. label distribution) of a sample. However, the label distribution is not a complete representation of an instance because it overlooks the absolute intensity of each label. Specifically, it's impossible to obtain the total description degree of hidden labels that not in the label space, which leads to the loss of information and confusion in instances. To solve the above problem, we come up with a new concept named background concentration to serve as the absolute description degree term of the label distribution and introduce it into the LDL process, forming the improved paradigm of concentration distribution learning. Moreover, we propose a novel model by probabilistic methods and neural networks to learn label distributions and background concentrations from existing LDL datasets. Extensive experiments prove that the proposed approach is able to extract background concentrations from label distributions while producing more accurate prediction results than the state-of-the-art LDL methods. The code is available in https://github.com/seutjw/CDL-LD.