Generative image inpainting for link prediction

摘要

Link prediction is a fundamental task that predicts whether a link exists between two nodes based on the currently observed network. Existing approaches such as heuristic-based algorithms assume that two nodes are likely to have a link in a network. In fact, they limit algorithm effectiveness when the assumptions are not correct. Moreover, these link prediction algorithms lack generalization ability, which indicates that they have different effects on different types of networks. For example, the common neighbours algorithm works well on social networks, but it shows poor performance on electric power networks. Inspired by the image inpainting technology of generative adversarial networks and the adjacency matrix representation of networks, we propose a new framework for link prediction based on the image inpainting method, named the Generative Image Inpainting for Link Prediction algorithm (GIILP), to address these problems. The key idea of the GIILP is that the network can be converted into an image (the image is a form of the adjacency matrix (two dimensions)). Pixel values represent the likelihood of two nodes. Thus, the problem of predicting a possible link between nodes is converted into filling missing pixels in an image. The link information of the network can be expressed by the image information, which means that our algorithm does not need assumptions such as heuristics, and works regardless of the dataset type. The experimental results on multiple link prediction public datasets demonstrate that our algorithm has an advantage over other algorithms, including heuristic-based and deep learning methods.