Link prediction is a demanding task in real-world scenarios, such as recommender systems, which targets to predict the unobservable links between different objects by learning network-structured data. In this paper, we propose a novel multi-view graph convolutional neural network (MV-GCN) model to solve this problem based on Matrix Completion method by simultaneously exploiting the interactive relationship and the content information of different objects. Unlike existing approaches directly concatenate the interactive and content information as a single view, the proposed MV-GCN improves the accuracy of the predictions by restricting the consistencies on the graph embedding from multiple views. Experimental results on six primary benchmark datasets, including two homogeneous datasets and four heterogeneous datasets, both show that MV-GCN outperforms the recent state-of-the-art methods.

No abstract

No abstract

Retinal vessel segmentation based on deep learning requires a lot of manual labeled data. That's time-consuming, laborious and professional. In this paper, we propose a data-efficient semi-supervised learning framework, which effectively combines the existing deep learning network with generative adversarial networks (GANs) and self-training ideas. In view of the difficulty of tuning hyper-parameters of semi-supervised learning, we propose a method for hyper-parameters selection based on particle swarm optimization (PSO) algorithm. This work is the first demonstration that combines intelligent optimization with semi-supervised learning for achieving the best performance. Under the collaboration of adversarial learning, self-training and PSO, we obtain the performance of retinal vessel segmentation approximate to or even better than representative supervised learning using only one tenth of the labeled data from DRIVE.