The proposed Weakly-Dependent on Graph Low-Rank Tensor Completion method achieved a Mean Square Error of 2.68x10^6, outperforming baseline methods for metro passenger flow prediction.
A novel low-rank CP tensor decomposition framework with graph penalties improves the accuracy of metro passenger flow prediction compared to standard tensor completion methods.
Absolute Event Rate: 2.68% vs 3.98%
Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data. However, low-rank structure is a global property, which will not be fulfilled when the data presents complex and weak dependencies given specific graph structures. One particular application that motivates this study is the spatiotemporal data analysis. As shown in the preliminary study, weakly dependencies can worsen the low-rank tensor completion performance. In this paper, we propose a novel low-rank CANDECOMP / PARAFAC (CP) tensor decomposition and completion framework by introducing the L1-norm penalty and Graph Laplacian penalty to model the weakly dependency on graph. We further propose an efficient optimization algorithm based on the Block Coordinate Descent for efficient estimation. A case study based on the metro passenger flow data in Hong Kong is conducted to demonstrate an improved performance over the regular tensor completion methods.
Li et al. (Fri,) conducted a other in Metro passenger flow prediction. Weakly-Dependent on Graph Low-Rank Tensor Completion (WDGTC) vs. Other tensor completion methods (geomCG, HaLRTC, FBCP, TREL1 CP, TDVM CP, MTIOP#LRS) was evaluated on Mean Square Error (MSE) for passenger flow prediction. The proposed Weakly-Dependent on Graph Low-Rank Tensor Completion method achieved a Mean Square Error of 2.68x10^6, outperforming baseline methods for metro passenger flow prediction.