Comprehensive comparative study of multi-label classification methods

Multi-label classification (MLC) has recently attracted increasing interest in the machine learning community. Several studies provide surveys of methods and datasets for MLC, a few empirical comparisons MLC methods. However, they are limited number considered. This paper provides comprehensive investigation wide range on wealth from different domains. More specifically, our study evaluates 26 42 benchmark using 20 evaluation measures. The methodology used meets highest literature standards designing conducting large-scale, time-limited experimental studies. First, were selected based their use community to ensure balanced representation across taxonomy within study. Second, cover complexity application measures assess predictive performance efficiency results analysis identify RFPCT, RFDTBR, ECCJ48, EBRJ48, AdaBoost.MH as best-performing spectrum Whenever new method is introduced, it should be compared with subsets according relevant (and possibly different) criteria.