Pooling homogeneous ensembles to build heterogeneous ensembles

In ensemble methods, the outputs of a collection of diverse classifiers are combined in the expectation that the global prediction be more accurate than the individual ones. Heterogeneous ensembles consist of predictors of different types, which are likely to have different biases. If these biases are complementary, the combination of their decisions is beneficial. In this work, a family of heterogeneous ensembles is built by pooling classifiers from M homogeneous ensembles of different types of size T. Depending on the fraction of base classifiers of each type, a particular heterogeneous combination in this family is represented by a point in a regular simplex in M dimensions. The M vertices of this simplex represent the different homogeneous ensembles. A displacement away from one of these vertices effects a smooth transformation of the corresponding homogeneous ensemble into a heterogeneous one. The optimal composition of such heterogeneous ensemble can be determined using cross-validation or, if bootstrap samples are used to build the individual classifiers, out-of-bag data. An empirical analysis of such combinations of bootstraped ensembles composed of neural networks, SVMs, and random trees (i.e. from a standard random forest) illustrates the gains that can be achieved by this heterogeneous ensemble creation method.

Vote-boosting ensembles

Vote-boosting is a sequential ensemble learning method in which the individual classifiers are built on different weighted versions of the training data. To build a new classifier, the weight of each training instance is determined in terms of the degree of disagreement among the current ensemble predictions for that instance. For low class-label noise levels, especially when simple base learners are used, emphasis should be made on instances for which the disagreement rate is high. When more flexible classifiers are used and as the noise level increases, the emphasis on these uncertain instances should be reduced. In fact, at sufficiently high levels of class-label noise, the focus should be on instances on which the ensemble classifiers agree. The optimal type of emphasis can be automatically determined using cross-validation. An extensive empirical analysis using the beta distribution as emphasis function illustrates that vote-boosting is an effective method to generate ensembles that are both accurate and robust.