TY - CONF ID - jf:ECML-09-QuickECOC T1 - Efficient Decoding of Ternary Error-Correcting Output Codes for Multiclass Classification A1 - Park, Sang-Hyeun A1 - Fürnkranz, Johannes ED - Buntine, Wray L. ED - Grobelnik, Marko ED - Mladenić, Dunja ED - Shawe-Taylor, John TI - Proceedings of the 20th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2009, Bled, Slovenia), Part II Y1 - 2009 SP - 189 EP - 204 PB - Springer M2 - doi: 10.1007/978-3-642-04174-7_13 N2 - We present an adaptive decoding algorithm for ternary ECOC matrices which reduces the number of needed classifier evaluations for multiclass classification. The resulting predictions are guaranteed to be equivalent with the original decoding strategy except for ambiguous final predictions. The technique works for Hamming Decoding and several commonly used alternative decoding strategies. We show its effectiveness in an extensive empirical evaluation considering various code design types: Nearly in all cases, a considerable reduction is possible. We also show that the performance gain depends on the sparsity and the dimension of the ECOC coding matrix. ER -