Round Robin Classification

By Johannes Fürnkranz. Journal of machine learning research, 2002

470 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/83d40f5e09b1143464d9c297bdb8c571e9a5ad4c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Investigation of the random forest framework for classification of hyperspectral data (2005, background): “framework has been shown to be more successful than traditional 1-of- classifiers for many problems involving large output spaces [18].”
Label ranking by learning pairwise preferences (2008, methodology): “The key idea of pairwise learning is well-known in the context of classification (Fürnkranz, 2002), where it allows one to transform a multi-class classification problem, i.e., a problem involving c > 2 classes L = {λ 1 . . . λ c }, into a number of binary problems.”
Learning shared subspace for multi-label dimensionality reduction via dependence maximization (2015, methodology): “Some prominent examples include binary relevance method [7], pair-wise method [16,17] and label embedding method [18–20].”
An extensive experimental comparison of methods for multi-label learning (2012, methodology): “The simplest strategies in the multi-label setting are the one-against-all and one-against-one strategies, also referred to as the binary relevance method [2] and pair-wise method [13,14], respectively.”
Multilabel classification via calibrated label ranking (2008, background): “Proof In previous work, it has been shown that training a pairwise classifier requires O(cn) training examples (Fürnkranz 2002).”
SMOTE-RSB*: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory (2012, methodology): “When multiple classes are present, the binary-class approach may be directly applicable via pairwise coupling techniques [15].”
Advances in Intelligent Data Analysis V (2003, methodology): “In this paper, we propose fuzzy sets in the form of flexible constraints [4,3,7] as a means for regularization or, more specifically, for expressing background knowledge about a functional relation to be learned.”
Multi-class pattern classification using neural networks (2007, methodology): “[23] , shows an optimal classification boundary for a six-class pattern classification problem, which is possible to be drawn by a single neural network system since it is trained with the presence of the knowledge of all pattern classes.”
Classifier chains for multi-label classification (2009, methodology): “CLR (Fürnkranz et al. 2008) is a well-known example (many other pairwise methods are specific to the label ranking problem, which is beyond the scope of this paper). In Petrovskiy (2006), each pairwise classifier is accompanied by two probabilistic models to isolate the overlapping attribute space.”
An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes (2011, methodology): “These classifiers are usually referred to as base learners or base classifiers of the system [30].”