Workshop: Second Workshop on Quantum Tensor Networks in Machine Learning
Graph-Tensor Singular Value Decomposition for Data Recovery
Lei Deng · Haifeng Zheng · Xiao-Yang Liu
In real-world scenarios, data are commonly generated with graph structures, e.g., sensory data in transportation networks, user profiles in social networks, and traffic trace data in Internet. Incomplete graph data limits further data analysis. Hence recovering missing graph data becomes crucial. In this work, we exploit graph-tensor decomposition strategies for data recovery. Experimental results show that the recovery performance of graph data can be significantly improved by adopting graph-tensor decomposition.