Towards Multilabel Rule Learning

In this position paper, we provide first insights into possible schemes to utilize rule learning algorithms to solve the task of multilabel classification. The main idea is to exploit specific properties of symbolic rule representations to build models that consist of high-quality multilabel rules. To this end, novel ideas which rely on the adaptation of conventional inductive rule learners to multilabel data are presented. Their expected advantages and disadvantages, opportunities and limitations are reviewed and discussed.

[1]  Pericles A. Mitkas,et al.  Effective Rule-Based Multi-label Classification with Learning Classifier Systems , 2013, ICANNGA.

[2]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[3]  K. Dembczynski,et al.  On Label Dependence in Multi-Label Classification , 2010 .

[4]  Pedro M. Domingos.  Towards a Unified Approach to Concept Learning , 1996, AAAI/IAAI, Vol. 2.

[5]  Yihong Gong,et al.  Multi-labelled classification using maximum entropy method , 2005, SIGIR '05.

[6]  Andrew McCallum,et al.  Collective multi-label classification , 2005, CIKM '05.

[7]  Peter I. Cowling,et al.  MMAC: a new multi-class, multi-label associative classification approach , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[8]  Geoff Holmes,et al.  Classifier chains for multi-label classification , 2009, Machine Learning.

[9]  Sebastián Ventura,et al.  Evolving Multi-label Classification Rules with Gene Expression Programming: A Preliminary Study , 2010, HAIS.

[10]  Sung-Bae Cho,et al.  An Evolutionary Multi Label Classification using Associative Rule Mining for Spatial Preferences , 2011 .

[11]  Peter I. Cowling,et al.  Knowledge and Information Systems , 2006 .

[12]  Eyke Hüllermeier,et al.  Bayes Optimal Multilabel Classification via Probabilistic Classifier Chains , 2010, ICML.

[13]  JOHANNES FÜRNKRANZ,et al.  Separate-and-Conquer Rule Learning , 1999, Artificial Intelligence Review.

[14]  Mohammed J. Zaki,et al.  Multi-label Lazy Associative Classification , 2007, PKDD.

[15]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[16]  Bo Li,et al.  Multi-label Classification based on Association Rules with Application to Scene Classification , 2008, 2008 The 9th International Conference for Young Computer Scientists.

[17]  Rémi Gilleron,et al.  Learning Multi-label Alternating Decision Trees from Texts and Data , 2003, MLDM.