%Aigaion2 BibTeX export from Knowledge Engineering Publications %Friday 17 December 2021 11:56:32 PM @INPROCEEDINGS{mr:ML-Consistency-Coverage, author = {Rapp, Michael and Loza Menc{\'{\i}}a, Eneldo and F{\"{u}}rnkranz, Johannes}, editor = {Kralj Novak, Petra and {\v S}muc, Tomislav and D{\v z}eroski, Sa{\v s}o}, keywords = {heuristics, multilabel classification, Rule Learning}, month = oct, title = {On the Trade-off Between Consistency and Coverage in Multi-label Rule Learning Heuristics}, booktitle = {Discovery Science}, year = {2019}, pages = {96--111}, publisher = {Springer International Publishing}, address = {Cham}, isbn = {978-3-030-33778-0}, url = {https://arxiv.org/abs/1908.03032}, doi = {10.1007/978-3-030-33778-0_9}, abstract = {Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning algorithms employ a heuristic-guided search for rules that model regularities contained in the training data and it is commonly accepted that the choice of the heuristic has a significant impact on the predictive performance of the learner. Whereas the properties of rule learning heuristics have been studied in the realm of single-label classification, there is no such work taking into account the particularities of multi-label classification. This is surprising, as the quality of multi-label predictions is usually assessed in terms of a variety of different, potentially competing, performance measures that cannot all be optimized by a single learner at the same time. In this work, we show empirically that it is crucial to trade off the consistency and coverage of rules differently, depending on which multi-label measure should be optimized by a model. Based on these findings, we emphasize the need for configurable learners that can flexibly use different heuristics. As our experiments reveal, the choice of the heuristic is not straight-forward, because a search for rules that optimize a measure locally does usually not result in a model that maximizes that measure globally.} }