Applying Differential Privacy to Tensor Completion

Zheng Wei, Zhengpin Li, Xiaojun Mao, Jian Wang

Abstract: Tensor completion aims at filling the missing or unobserved en-tries based on partially observed tensors. However, utilization of the observed tensors often raises serious privacy concerns in many practical scenarios. To address this issue, we propose a solid and unified framework that contains several approaches for applying differential privacy to the two most widely used tensor decomposition methods: i) CANDECOMP/PARAFAC and ii) Tucker decompositions. For each approach, we establish a rigorous privacy guarantee and meanwhile evaluate the privacy-accuracy trade-off. Experiments on synthetic datasets demonstrate that our proposal achieves high accuracy for tensor completion while ensuring strong privacy protections.