Search

Co-training is an effective semi-supervised learning method which uses unlabeled instances to improve prediction accuracy. In the co-training process, a random sampling is used to gradually select unlabeled instances to train classifiers. In this paper we explore whether other sampling methods can improve co-training performance. A novel selective sampling method, agreement-based sampling, is proposed. Experimental results show that our new sampling method can improve co-training significantly. [ABSTRACT FROM AUTHOR]

Decision trees have been widely used in many data mining applications due to their interpretable representation. However, learning an accurate decision tree model often requires a large amount of labeled training data. Labeling data is costly and time consuming. In this paper, we study learning decision trees with lesser labeling cost from two perspectives: data quality and data quantity. At each step of active learning process we learn a random forest and then use it to label a large quantity of unlabeled data. To overcome the large tree size caused by the machine labeling, we generate weighted (soft) labeled data using the prediction confidence of the labeling classifier. Empirical studies show that our method can significantly improve active learning in terms of labeling cost for decision tree learning, and the improvement does not sacrifice the size of decision trees. [ABSTRACT FROM AUTHOR]

In many applications, an accurate ranking of instances is as important as accurate classification. However, it has been observed that traditional decision trees perform well in classification, but poor in ranking. In this paper, we point out that there is an inherent obstacle for traditional decision trees to achieving both accurate classification and ranking. We propose to understand decision trees from probabilistic perspective, and use probability theory to compute probability estimates and perform classification and ranking. The new model is called probabilistic inference trees (PITs). Our experiments show that the PIT learning algorithm performs well in both ranking and classification. More precisely, it significantly outperforms the state-of-the-art decision tree learning algorithms designed for ranking, such as C4.4 [10] and Ling and Yan's algorithm [6], and performs competitively with the traditional decision tree learning algorithms, such as C4.5, in classification. Our research provides a novel algorithm for the applications in which both accurate classification and ranking are desired. [ABSTRACT FROM AUTHOR]

In real-world data mining applications, an accurate ranking is as important as an accurate classification. Naive Bayes has been widely used in data mining as a simple and effective classification and ranking algorithm. Since its conditional independence assumption is rarely true, numerous algorithms have been proposed to improve naive Bayes, for example, SBC[1] and TAN[2]. Indeed, the experimental results show that SBC and TAN achieve a significant improvement in term of classification accuracy. However, unfortunately, our experiments also show that SBC and TAN perform even worse than naive Bayes in ranking measured by AUC[3,4](the area under the Receiver Operating Characteristics curve). This fact raises the question of whether we can improve Naive Bayes with both accurate classification and ranking? In this paper, responding to this question, we present a new learning algorithm called One Dependence Augmented Naive Bayes(ODANB). Our motivation is to develop a new algorithm to improve Naive Bayes' performance not only on classification measured by accuracy but also on ranking measured by AUC. We experimentally tested our algorithm, using the whole 36 UCI datasets recommended by Weka[5], and compared it to Naive Bayes, SBC and TAN. The experimental results show that our algorithm outperforms all the other algorithms significantly in yielding accurate ranking, yet at the same time outperforms all the other algorithms slightly in terms of classification accuracy. [ABSTRACT FROM AUTHOR]

Accurate probability-based ranking of instances is crucial in many real-world data mining applications. KNN (k-nearest neighbor) [1] has been intensively studied as an effective classification model in decades. However, its performance in ranking is unknown. In this paper, we conduct a systematic study on the ranking performance of KNN. At first, we compare KNN and KNNDW (KNN with distance weighted) to decision trees and naive Bayes in ranking, measured by AUC (the area under the Receiver Operating Characteristics curve). Then, we propose to improve the ranking performance of KNN by combining KNN with naive Bayes. The idea is that a naive Bayes is learned using the k nearest neighbors of the test instance as the training data and used to classify the test instance. A critical problem in combining KNN with naive Bayes is the lack of training data when k is small. We propose to deal with it using sampling to expand the training data. That is, each of the k nearest neighbors is "cloned" and the clones are added to the training data. We call our new model instance cloning local naive Bayes (simply ICLNB). We conduct extensive empirical comparison for the related algorithms in two groups in terms of AUC, using the 36 UCI datasets recommended by Weka[2]. In the first group, we compare ICLNB with other types of algorithms C4.4[3], naive Bayes and NBTree[4]. In the second group, we compare ICLNB with KNN, KNNDW and LWNB[5]. Our experimental results show that ICLNB outperforms all those algorithms significantly. From our study, we have two conclusions. First, KNN-relates algorithms performs well in ranking. Second, our new algorithm ICLNB performs best among the algorithms compared in this paper, and could be used in the applications in which an accurate ranking is desired. [ABSTRACT FROM AUTHOR]