Search

As a classification task, the detection of new malicious users in social networks has been facing the lack of datasets and labels of malicious users. With limited data, this paper proposed a method based on adaptive differential graph convolution to detect malicious users accurately. By extracting user features and social relationships in the social network, the method constructed the social network graph. After this, it calculated the similarities between node and its neighbors to prioritize the neighbors, and used the priority order to sample key neighbors. The node used adaptive weighted average to aggregate the features of key neighbors to itself, to update its features. After feature updating, by feature dimension reduction and normalization, the node got its malicious value, for malicious detection. The experiment results show that, compared to other methods, the method proposed in the paper achieves higher precision and overall accuracy on detection of new malicious users, with a satisfactory speed. Results also demonstrate that adaptive differential graph convolutional networks can effectively capture the key features of a small number of data samples. [ABSTRACT FROM AUTHOR]

Pilot contamination is the bottleneck of the massive MIMO systems. This paper proposed a pilot allocation scheme that combined user location and spatial distance. All users were clustered according to whether the angle of arrival overlapped, and classified the user sets whose arrival angles did not overlap with each other into n sets. Then the remaining users wh o did not satisfy the condition were classified into the n + 1 classes. It assigned n sets of pilot sequences to the first n types of user sets. For users in then+ 1 class set, the paper defined an interference function to construct a weighted graph. At the same time, it derived the user's expression of the uplink spectrum efficiency. The simulation results show that the scheme can significantly improve the spectrum efficiency. [ABSTRACT FROM AUTHOR]

To solve the problem of user cold start, the paper proposed a latent factor recommendation algorithm based on the user classification, which integrated user classification information into matrix factorization. Firstly, it created the classification rating matrix by using the method of index function and unifying based on the user-item rating matrix and user classification information, then it combined the data of classification rating matrix into the rating prediction stage in the latent factor model, and finally it used a number of latent factors to compare the new method with the traditional latent factor model. 'Hie experimental results show that the proposed model can not only solve the cold start problem, but also reduce the root mean squared error between predicted ratings and real ones, and improves the accuracy of prediction effectively. [ABSTRACT FROM AUTHOR]