2015 · 11 citations · 8 references
ComputingComputer ScienceData ScienceData MiningMachine LearningNatural Language ProcessingClassificationMachine Learning For Big DataRepresentation LearningSemi-supervised LearningText MiningBig Data ClassificationBinary RelevanceMulti-label RecognitionMulti-label Text ClassificationMultilabel ClassificationPredictive PerformancePredictive Performance EvaluationRelevance Judgments
The widely known classifier chains method for multi-label classification, which is based on the binary relevance (BR) method, overcomes the disadvantages of BR and achieves higher predictive performance, but still retains important advantages of BR, most importantly low time complexity. Nevertheless, despite its advantages, it is clear that a randomly arranged chain can be poorly ordered. We overcome this issue with a different strategy: Several times K-means algorithms are employed to get the correlations between labels and to confirm the order of binary classifiers. The algorithm ensure the right correlations be transmitted persistently as great as possible by improve the earlier predictions accuracy. The experimental results on the Reuters-21578 text chat data set and image data set show that the approach is efficient and appealing in most cases.
8
ML-KNN: A lazy learning approach to multi-label learning
Min-Ling Zhang, Zhi‐Hua Zhou · Pattern Recognition · 2007 · 3.5K citations
Classifier chains for multi-label classification
Jesse Read, Bernhard Pfahringer, Geoffrey Holmes et al. · Machine Learning · 2011 · 2.3K citations · Full text
Multi-label learning by exploiting label dependency
Min-Ling Zhang, Kun Zhang · 2010 · 415 citations
Generalized k-nearest neighbor rules
James C. Bezdek, Siew K. Chuah, David B. Leep · Fuzzy Sets and Systems · 1986 · 161 citations