Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
This work addresses efficiency and interpretability issues in spatial analysis for fields like geology and climate science, representing an incremental improvement over existing tensor methods.
The paper tackled the problem of computationally expensive and spatially incoherent tensor latent factor models for spatial analysis by developing the Multiresolution Tensor Learning (MRTL) algorithm, which achieved a 4-5x speedup compared to fixed-resolution approaches while producing accurate and interpretable results.
Efficient and interpretable spatial analysis is crucial in many fields such as geology, sports, and climate science. Tensor latent factor models can describe higher-order correlations for spatial data. However, they are computationally expensive to train and are sensitive to initialization, leading to spatially incoherent, uninterpretable results. We develop a novel Multiresolution Tensor Learning (MRTL) algorithm for efficiently learning interpretable spatial patterns. MRTL initializes the latent factors from an approximate full-rank tensor model for improved interpretability and progressively learns from a coarse resolution to the fine resolution to reduce computation. We also prove the theoretical convergence and computational complexity of MRTL. When applied to two real-world datasets, MRTL demonstrates 4~5x speedup compared to a fixed resolution approach while yielding accurate and interpretable latent factors.