Convolutional Graph-Tensor Net for Graph Data Completion
This addresses the problem of incomplete graph-structured data in applications like social networks and recommendation systems, representing an incremental improvement with specific performance gains.
The paper tackles the graph data completion problem by proposing a Convolutional Graph-Tensor Net (Conv GT-Net) that uses deep neural networks to learn transforms of graph-tensors, achieving a 50% higher completion accuracy and 3.6x to 8.1x faster completion speed compared to existing algorithms on ego-Facebook datasets.
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 $\sim$ 8.1x faster) over the existing algorithms.