Uncertainty quantified matrix completion using bayesian hierarchical matrix factorization

Farideh Fazayeli, Arindam Banerjee, Jens Kattge, Franziska Schrodt, Peter B. Reich

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Low-rank matrix completion methods have been successful in a variety of settings such as recommendation systems. However, most of the existing matrix completion methods only provide a point estimate of missing entries, and do not characterize uncertainties of the predictions. In this paper, we propose a Bayesian hierarchical probabilistic matrix factorization (BHPMF) model to 1) incorporate hierarchical side information, and 2) provide uncertainty quantified predictions. The former yields significant performance improvements in the problem of plant trait prediction, a key problem in ecology, by leveraging the taxonomic hierarchy in the plant kingdom. The latter is helpful in identifying predictions of low confidence which can in turn be used to guide field work for data collection efforts. A Gibbs sampler is designed for inference in the model. Further, we propose a multiple inheritance BHPMF (MI-BHPMF) which can work with a general directed acyclic graph (DAG) structured hierarchy, rather than a tree. We present comprehensive experimental results on the problem of plant trait prediction using the largest database of plant traits, where BHPMF shows strong empirical performance in uncertainty quantified trait prediction, outperforming the state-of-the-art based on point estimates. Further, we show that BHPMF is more accurate when it is confident, whereas the error is high when the uncertainty is high.

Original languageEnglish (US)
Title of host publicationProceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014
EditorsCesar Ferri, Guangzhi Qu, Xue-wen Chen, M. Arif Wani, Plamen Angelov, Jian-Huang Lai
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages312-317
Number of pages6
ISBN (Electronic)9781479974153
DOIs
StatePublished - Feb 5 2014
Event2014 13th International Conference on Machine Learning and Applications, ICMLA 2014 - Detroit, United States
Duration: Dec 3 2014Dec 6 2014

Publication series

NameProceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014

Other

Other2014 13th International Conference on Machine Learning and Applications, ICMLA 2014
CountryUnited States
CityDetroit
Period12/3/1412/6/14

Keywords

  • Bayesian Analysis
  • Probabilistic Matrix Factorization
  • Uncertainty Quantification

Fingerprint Dive into the research topics of 'Uncertainty quantified matrix completion using bayesian hierarchical matrix factorization'. Together they form a unique fingerprint.

  • Cite this

    Fazayeli, F., Banerjee, A., Kattge, J., Schrodt, F., & Reich, P. B. (2014). Uncertainty quantified matrix completion using bayesian hierarchical matrix factorization. In C. Ferri, G. Qu, X. Chen, M. A. Wani, P. Angelov, & J-H. Lai (Eds.), Proceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014 (pp. 312-317). [7033133] (Proceedings - 2014 13th International Conference on Machine Learning and Applications, ICMLA 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2014.56