Loading...
Please wait, while we are loading the content...
Similar Documents
Under consideration for publication in Knowledge and Information Systems Solving Multi-Instance Problems with Classifier Ensemble Based on Constructive Clustering (2005)
| Content Provider | CiteSeerX |
|---|---|
| Author | Zhang, Min-Ling Zhou, Zhi-Hua |
| Abstract | Abstract. In multi-instance learning, the training set is composed of labeled bags each consists of many unlabeled instances, that is, an object is represented by a set of feature vectors instead of only one feature vector. Most current multi-instance learning algorithms work through adapting single-instance learning algorithms to the multi-instance representation, while this paper proposes a new solution which goes at an opposite way, that is, adapting the multi-instance representation to single-instance learning algorithms. In detail, the instances of all the bags are collected together and clustered into d groups at first. Each bag is then re-represented by d binary features, where the value of the i-th feature is set to one if the concerned bag has instances falling into the i-th group and zero otherwise. Thus, each bag is represented by one feature vector so that single-instance classifiers can be used to distinguish different classes of bags. Through repeating the above process with different values of d, many classifiers can be generated and then they can be combined into an ensemble for prediction. Experiments show that the proposed method works well on standard as well as generalized multi-instance problems. |
| File Format | |
| Publisher Date | 2005-01-01 |
| Access Restriction | Open |
| Subject Keyword | Single-instance Classifier Binary Feature Opposite Way Feature Vector Multi-instance Problem Different Value Information System Solving Multi-instance Problem Different Class Multi-instance Learning New Solution Many Classifier Classifier Ensemble Constructive Clustering Many Unlabeled Instance I-th Group Multi-instance Representation Training Set Current Multi-instance Learning Algorithm Work Concerned Bag I-th Feature |
| Content Type | Text |
| Resource Type | Article |
