On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition Property

The benefit of exploiting label dependence in multi-label classification is known to be closely dependent on the type of loss to be minimized. In this paper, we show that the subsets of labels that appear as irreducible factors in the factorization of the conditional distribution of the label set given the input features play a pivotal role for multi-label classification in the context of 0/1 loss minimization, as they divide the learning task into simpler independent multi-class problems. We establish theoretical results to characterize and identify these irreducible label factors for any given probability distribution satisfying the Composition property. The analysis lays the foundation for generic multi-label classification and optimal feature subset selection procedures under this subclass of distributions. Our conclusions are supported by carefully designed experiments on synthetic and benchmark data.