Trust prediction based on extreme learning machine and asymmetric tri-training

• Published in: IEEE access Vol. 9; p. 1
• Main Authors: Wang, Yan, Tong, Xiangrong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-01-2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Asymmetric tri-training; Asymmetry; Classifiers; Evaluation; extreme learning machine; Extreme learning machines; Machine learning; Neural networks; Prediction algorithms; Predictive models; pseudo label; Social networking (online); Social networks; Stability analysis; Training; Transfer learning; trust prediction; Trustworthiness
• DOI: 10.1109/ACCESS.2021.3075952
• EISSN: 2169-3536

Currently, more and more people communicate and trade through online social networks, so it is necessary to predict the trust between users. In order to predict the trust between users through a social network requires some other factors, such as user similarity, topic relevance, and the number of common neighbors should be considered. Some scholars use BP neural network based on the asymmetric tri-training model to train one social network and use transfer learning to predict the social relationship of another social network. However, this method has high computational complexity and slow operation speed. To solve the problem, the three classifiers are expanded into four classifiers on the basis of asymmetric tri-training, and the extreme learning machine classifier is used to replace the BP neural network classifier. The specific steps are: we first obtain the common features between different networks, use source data samples to train the first three classifiers, save the model, and train target samples to generate pseudo labels; then we use standard pseudo label samples to train the fourth classifier and use it to predict the social relations of the target network. Finally, compare with the existing evaluation methods,we proposed an algorithm on six online social networks. The experimental results show that the model in this paper is superior to other evaluation methods in recall and stability.