SSLfmm: An R Package for Semi-Supervised Learning with a Mixed-Missingness Mechanism in Finite Mixture Models

TL;DR

SSLfmm is an R package that models semi-supervised learning with mixed missingness mechanisms, leveraging label missingness information to improve classification in finite mixture models with Gaussian components.

Contribution

It introduces a novel approach to semi-supervised learning that accounts for both MCAR and MAR missingness, enhancing classifier estimation in finite mixture models.

Findings

Potentially lower misclassification rates than supervised methods

Effective modeling of mixed missingness improves estimation

Demonstrated through simulated examples

Abstract

Semi-supervised learning (SSL) constructs classifiers from datasets in which only a subset of observations is labelled, a situation that naturally arises because obtaining labels often requires expert judgement or costly manual effort. This motivates methods that integrate labelled and unlabelled data within a learning framework. Most SSL approaches assume that label absence is harmless, typically treated as missing completely at random or ignored, but in practice, the missingness process can be informative, as the chances of an observation being unlabelled may depend on the ambiguity of its feature vector. In such cases, the missingness indicators themselves provide additional information that, if properly modelled, may improve estimation efficiency. The \textbf{SSLfmm} package for R is designed to capture this behaviour by estimating the Bayes' classifier under a finite mixture model in which each component corresponding to a class follows a multivariate normal distribution. It incorporates a mixed-missingness mechanism that combines a missing completely at random (MCAR) component with a (non-ignorable) missing at random (MAR) component, the latter modelling the probability of label missingness as a logistic function of the entropy based on the features. Parameters are estimated via an Expectation--Conditional Maximisation algorithm. In the two-class Gaussian setting with arbitrary covariance matrices, the resulting classifier trained on partially labelled data may, in some cases, achieve a lower misclassification rate than the supervised version in the case where all the labels are known. The package includes a practical tool for modelling and illustrates its performance through simulated examples.