LGMLDec 3, 2019

A Hidden Variables Approach to Multilabel Logistic Regression

arXiv:1912.01241v1
Originality Incremental advance
AI Analysis

This addresses multilabel classification problems in domains like text categorization and music annotation, but it is incremental as it builds on existing logistic regression methods.

The paper tackles multilabel classification by introducing a probabilistic model, MLRH, which extends logistic regression with hidden variables to relax one-hot-encoding constraints, achieving competitive performance on benchmark datasets.

Multilabel classification is an important problem in a wide range of domains such as text categorization and music annotation. In this paper, we present a probabilistic model, Multilabel Logistic Regression with Hidden variables (MLRH), which extends the standard logistic regression by introducing hidden variables. Hidden variables make it possible to go beyond the conventional multiclass logistic regression by relaxing the one-hot-encoding constraint. We define a new joint distribution of labels and hidden variables which enables us to obtain one classifier for multilabel classification. Our experimental studies on a set of benchmark datasets demonstrate that the probabilistic model can achieve competitive performance compared with other multilabel learning algorithms.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes