{"type":"journal_article","file":[{"date_created":"2018-11-02T15:30:57Z","file_size":1482882,"access_level":"closed","date_updated":"2018-11-02T15:30:57Z","content_type":"application/pdf","file_id":"5305","relation":"main_file","creator":"ups","success":1,"file_name":"OnTheEffectivenessOfHeuristics.pdf"}],"_id":"3402","date_updated":"2022-01-06T06:59:14Z","file_date_updated":"2018-11-02T15:30:57Z","abstract":[{"lang":"eng","text":"In machine learning, so-called nested dichotomies are utilized as a reduction technique, i.e., to decompose a multi-class classification problem into a set of binary problems, which are solved using a simple binary classifier as a base learner. The performance of the (multi-class) classifier thus produced strongly depends on the structure of the decomposition. In this paper, we conduct an empirical study, in which we compare existing heuristics for selecting a suitable structure in the form of a nested dichotomy. Moreover, we propose two additional heuristics as natural completions. One of them is the Best-of-K heuristic, which picks the (presumably) best among K randomly generated nested dichotomies. Surprisingly, and in spite of its simplicity, it turns out to outperform the state of the art."}],"publication_identifier":{"issn":["1573-0565"]},"author":[{"full_name":"Melnikov, Vitalik","last_name":"Melnikov","first_name":"Vitalik"},{"full_name":"Hüllermeier, Eyke","id":"48129","first_name":"Eyke","last_name":"Hüllermeier"}],"date_created":"2018-06-29T07:44:26Z","status":"public","ddc":["000"],"has_accepted_license":"1","title":"On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis","year":"2018","publication":"Machine Learning","doi":"10.1007/s10994-018-5733-1","project":[{"_id":"11","name":"SFB 901 - Subproject B3"},{"_id":"3","name":"SFB 901 - Project Area B"},{"name":"SFB 901","_id":"1"}],"user_id":"15504","language":[{"iso":"eng"}],"department":[{"_id":"355"}],"citation":{"apa":"Melnikov, V., &#38; Hüllermeier, E. (2018). On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis. <i>Machine Learning</i>. <a href=\"https://doi.org/10.1007/s10994-018-5733-1\">https://doi.org/10.1007/s10994-018-5733-1</a>","chicago":"Melnikov, Vitalik, and Eyke Hüllermeier. “On the Effectiveness of Heuristics for Learning Nested Dichotomies: An Empirical Analysis.” <i>Machine Learning</i>, 2018. <a href=\"https://doi.org/10.1007/s10994-018-5733-1\">https://doi.org/10.1007/s10994-018-5733-1</a>.","short":"V. Melnikov, E. Hüllermeier, Machine Learning (2018).","bibtex":"@article{Melnikov_Hüllermeier_2018, title={On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis}, DOI={<a href=\"https://doi.org/10.1007/s10994-018-5733-1\">10.1007/s10994-018-5733-1</a>}, journal={Machine Learning}, author={Melnikov, Vitalik and Hüllermeier, Eyke}, year={2018} }","mla":"Melnikov, Vitalik, and Eyke Hüllermeier. “On the Effectiveness of Heuristics for Learning Nested Dichotomies: An Empirical Analysis.” <i>Machine Learning</i>, 2018, doi:<a href=\"https://doi.org/10.1007/s10994-018-5733-1\">10.1007/s10994-018-5733-1</a>.","ama":"Melnikov V, Hüllermeier E. On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis. <i>Machine Learning</i>. 2018. doi:<a href=\"https://doi.org/10.1007/s10994-018-5733-1\">10.1007/s10994-018-5733-1</a>","ieee":"V. Melnikov and E. Hüllermeier, “On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis,” <i>Machine Learning</i>, 2018."}}