Sparse-Group Bayesian Feature Selection Using Expectation Propagation for Signal Recovery and Network Reconstruction
This is an incremental improvement for researchers in bioinformatics and machine learning, addressing inefficiencies in existing Bayesian and lasso methods for tasks like gene regulatory network reconstruction.
The authors tackled the problem of feature selection with grouping information by developing a Bayesian sparse-group method using expectation propagation, which achieved accurate parameter recovery and enabled large-scale network reconstruction with competitive performance in feature selection, prediction, and computing time.
We present a Bayesian method for feature selection in the presence of grouping information with sparsity on the between- and within group level. Instead of using a stochastic algorithm for parameter inference, we employ expectation propagation, which is a deterministic and fast algorithm. Available methods for feature selection in the presence of grouping information have a number of short-comings: on one hand, lasso methods, while being fast, underestimate the regression coefficients and do not make good use of the grouping information, and on the other hand, Bayesian approaches, while accurate in parameter estimation, often rely on the stochastic and slow Gibbs sampling procedure to recover the parameters, rendering them infeasible e.g. for gene network reconstruction. Our approach of a Bayesian sparse-group framework with expectation propagation enables us to not only recover accurate parameter estimates in signal recovery problems, but also makes it possible to apply this Bayesian framework to large-scale network reconstruction problems. The presented method is generic but in terms of application we focus on gene regulatory networks. We show on simulated and experimental data that the method constitutes a good choice for network reconstruction regarding the number of correctly selected features, prediction on new data and reasonable computing time.