Title :
An improved learning with local and global consistency
Author :
Li, Ming ; Zhang, Xiaoli ; Wang, Xuesong
Author_Institution :
Sch. of Inf. & Electr. Eng., China Univ. of Min. & Technol., Xuzhou, China
Abstract :
Learning with local and global consistency (LLGC) algorithm can effectively label a data, but it is helpless for noise data. The reason is that the LLGC algorithm will predict a label for each unlabelled data without taking into account whether a data has noise or not. Aiming at the deficiency of the LLGC algorithm, an improved version for semi-supervised learning algorithm with local and global consistency is proposed in this paper. At first, we compute the similarity of each data to all classes. And then the data can be ascribed to one class according to its similarities. The improved LLGC algorithm not only can label data as the conventional LLGC, but also can identify noise existed in data set effectively. Simulation results show that the improved LLGC algorithm can effectively avoid noise data being viewed as normal data.
Keywords :
learning (artificial intelligence); LLGC algorithm; global consistency; improved learning; local consistency; noise data; semisupervised learning algorithm; unlabelled data; Clustering algorithms; Computational modeling; Electronic mail; Learning systems; Machine learning; Machine learning algorithms; Prediction algorithms; Semisupervised learning; Supervised learning; Unsupervised learning; Graph; Learning with local and global consistency; Noise data; Semi-supervised learning; Similarity;
Conference_Titel :
Control and Decision Conference (CCDC), 2010 Chinese
Conference_Location :
Xuzhou
Print_ISBN :
978-1-4244-5181-4
Electronic_ISBN :
978-1-4244-5182-1
DOI :
10.1109/CCDC.2010.5498148
