Convolutional Graph-Tensor Net for Graph Data Completion

Graph data completion is a fundamentally important issue as data generally has a graph structure, e.g., social networks, recommendation systems, and the Internet of Things. We consider a graph where each node has a data matrix, represented as a textitgraph-tensor by stacking the data matrices in the third dimension. In this paper, we propose a textitConvolutional Graph-Tensor Net (textitConv GT-Net) for the graph data completion problem, which uses deep neural networks to learn the general transform of graph-tensors. The experimental results on the ego-Facebook data sets show that the proposed textitConv GT-Net achieves significant improvements on both completion accuracy (50% higher) and completion speed (3.6x ~ 8.1x faster) over the existing algorithms.