Abstract
Label distribution learning (LDL) is a novel machine learning paradigm to deal with label ambiguity issues by placing more emphasis on how relevant each label is to a particular instance. Many
LDL algorithms have been proposed and most of
them concentrate on the learning models, while few
of them focus on the feature selection problem. All
existing LDL models are built on a simple feature
space in which all features are shared by all the
class labels. However, this kind of traditional data
representation strategy tends to select features that
are distinguishable for all labels, but ignores labelspecific features that are pertinent and discriminative for each class label. In this paper, we propose
a novel LDL algorithm by leveraging label-specific
features. The common features for all labels and
specific features for each label are simultaneously
learned to enhance the LDL model. Moreover, we
also exploit the label correlations in the proposed
LDL model. The experimental results on several
real-world data sets validate the effectiveness of our
method