Multi-Label Learning Based on Transfer Learning and Label Correlation

In recent years,multi-label learning has received a lot of attention.However,most of the existing methods only consider global label correlation or local label correlation.In fact,on the one hand,both global and local label correlations can appear in real-world situation at same time.On the other hand,we should not be limited to pairwise labels while ignoring the high-order label correlation.In this paper,we propose a novel and effective method called GLLCBN for multi-label learning.Firstly,we obtain the global label correlation by exploiting label semantic similarity.Then,we analyze the pairwise labels in the label space of the data set to acquire the local correlation.Next,we build the original version of the label dependency model by global and local label correlations.After that,we use graph theory,probability theory and Bayesian networks to eliminate redundant dependency structure in the initial version model,so as to get the optimal label dependent model.Finally,we obtain the feature extraction model by adjusting the Inception V3 model of convolution neural network and combine it with the GLLCBN model to achieve the multi-label learning.The experimental results show that our proposed model has better performance than other multi-label learning methods in performance evaluating.

Personalized News Recommendation Based on the Text and Image Integration

The personalized news recommendation has been very popular in the news recommendation field.In most research,the picture information in the news is ignored,but the information conveyed to the users through pictures is more intuitive and more likely to affect the users’reading interests than the one in the textual form.Therefore,in this paper,a model that combines images and texts in the news is proposed.In this model,the new tags are extracted from the images and texts in the news,and based on these new tags,an adaptive tag(AT)algorithm is proposed.The AT algorithm selects the tags the user is interested in based on the user feedback.In particular,the AT algorithm can predict tags that a user may be interested in with the help of the tag correlation graph without any user feedback.The proposed AT algorithm is verified by experiments.The experimental results verified the AT algorithm regarding three evaluation indexes F1-score(F1),area under curve(AUC)and mean reciprocal rank(MRR).The recommended effect of the proposed algorithm is found to be better than those of the various baseline algorithms on real-world datasets.