E
Eemeli Leppäaho
Researcher at Helsinki Institute for Information Technology
Publications - 14
Citations - 279
Eemeli Leppäaho is an academic researcher from Helsinki Institute for Information Technology. The author has contributed to research in topics: Canonical correlation & Embarrassingly parallel. The author has an hindex of 7, co-authored 13 publications receiving 243 citations. Previous affiliations of Eemeli Leppäaho include Aalto University.
Papers
More filters
Journal ArticleDOI
Group Factor Analysis
TL;DR: Group Factor Analysis (GFA) as mentioned in this paper is an extension of canonical correlation analysis to more than two sets, in a way that is more flexible than previous extensions, and it is formulated as a variational inference of a latent variable model with structural sparsity.
Posted Content
Group Factor Analysis
TL;DR: The resulting solution solves the group factor analysis (GFA) problem accurately, outperforming alternative FA-based solutions as well as more straightforward implementations of GFA.
Journal ArticleDOI
Sparse group factor analysis for biclustering of multiple data sources
TL;DR: A Bayesian approach for joint bic Lustering of multiple data sources is presented, extending a recent method Group Factor Analysis to have a biclustering interpretation with additional sparsity assumptions, and enables data-driven detection of linear structure present in parts of the data sources.
Journal ArticleDOI
Bayesian multi-tensor factorization
TL;DR: Bayesian multi-tensor factorization is introduced, a model that is the first Bayesian formulation for joint factorization of multiple matrices and tensors, and the performance against existing baselines in multiple tensor factorization tasks in structural toxicogenomics and functional neuroimaging is demonstrated.
Journal Article
GFA: exploratory analysis of multiple data sources with group factor analysis
TL;DR: The R package GFA provides a full pipeline for factor analysis of multiple data sources that are represented as matrices with co-occurring samples, allowing learning dependencies between subsets of the data sources, decomposed into latent factors.