In multi-label learning, each training example is represented by a single instance while
associated with multiple labels, and the task is to predict a set of relevant labels for the
unseen instance. Existing approaches learn from multi-label data by assuming equal
labeling-importance, ie all the associated labels are regarded to be relevant while their
relative importance for the training example are not differentiated. Nonetheless, this
assumption fails to reflect the fact that the importance degree of each associated label is …

Multi-label learning deals with training examples each represented by a single instance
while associated with multiple class labels, and the task is to train a predictive model which
can assign a set of proper labels for the unseen instance. Existing approaches employ the
common assumption of equal labeling-importance, ie, all associated labels are regarded to
be relevant to the training instance while their relative importance in characterizing its
semantics are not differentiated. Nonetheless, this common assumption does not reflect the …