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 \textit{graph-tensor} by stacking the data matrices in the third dimension. In this paper, we propose a \textit{Convolutional Graph-Tensor Net} (\textit{Conv 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 \textit{Conv GT-Net} achieves significant improvements on both completion accuracy (50\% higher) and completion speed (3.6x ∼ 8.1x faster) over the existing algorithms.
@article{arxiv.2103.04485,
title = {Convolutional Graph-Tensor Net for Graph Data Completion},
author = {Xiao-Yang Liu and Ming Zhu},
journal= {arXiv preprint arXiv:2103.04485},
year = {2023}
}