Gap Filling in the Plant Kingdom---Trait Prediction Using Hierarchical Probabilistic Matrix Factorization

TL;DR

This paper introduces Hierarchical Probabilistic Matrix Factorization (HPMF), a novel method leveraging phylogenetic hierarchy to improve plant trait data prediction and fill missing data in large ecological databases.

Contribution

HPMF is the first matrix factorization approach that explicitly incorporates hierarchical phylogenetic information for trait prediction in plants.

Findings

HPMF achieves high accuracy in trait prediction.

Incorporating hierarchical structure improves performance.

HPMF captures trait correlations effectively.

Abstract

Plant traits are a key to understanding and predicting the adaptation of ecosystems to environmental changes, which motivates the TRY project aiming at constructing a global database for plant traits and becoming a standard resource for the ecological community. Despite its unprecedented coverage, a large percentage of missing data substantially constrains joint trait analysis. Meanwhile, the trait data is characterized by the hierarchical phylogenetic structure of the plant kingdom. While factorization based matrix completion techniques have been widely used to address the missing data problem, traditional matrix factorization methods are unable to leverage the phylogenetic structure. We propose hierarchical probabilistic matrix factorization (HPMF), which effectively uses hierarchical phylogenetic information for trait prediction. We demonstrate HPMF's high accuracy, effectiveness of incorporating hierarchical structure and ability to capture trait correlation through experiments.