Multi-version Tensor Completion for Time-delayed Spatio-temporal Data

TL;DR

This paper introduces a multi-version tensor completion method tailored for time-delayed spatio-temporal data, effectively handling non-random missingness and noise variations over time and location.

Contribution

It proposes a low-rank tensor model that captures dynamic updates in multi-version data, improving prediction accuracy over existing methods.

Findings

Achieves up to 27.2% lower RMSE than baseline methods.

Effectively models non-i.i.d. noise and missing data in real-world tensors.

Enables efficient tensor data tracking over time.

Abstract

Real-world spatio-temporal data is often incomplete or inaccurate due to various data loading delays. For example, a location-disease-time tensor of case counts can have multiple delayed updates of recent temporal slices for some locations or diseases. Recovering such missing or noisy (under-reported) elements of the input tensor can be viewed as a generalized tensor completion problem. Existing tensor completion methods usually assume that i) missing elements are randomly distributed and ii) noise for each tensor element is i.i.d. zero-mean. Both assumptions can be violated for spatio-temporal tensor data. We often observe multiple versions of the input tensor with different under-reporting noise levels. The amount of noise can be time- or location-dependent as more updates are progressively introduced to the tensor. We model such dynamic data as a multi-version tensor with an extra tensor mode capturing the data updates. We propose a low-rank tensor model to predict the updates over time. We demonstrate that our method can accurately predict the ground-truth values of many real-world tensors. We obtain up to 27.2% lower root mean-squared-error compared to the best baseline method. Finally, we extend our method to track the tensor data over time, leading to significant computational savings.