Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification

TL;DR

This paper introduces an interval type-2 fuzzy neural network model for multi-label classification, capturing label relationships more effectively than traditional binary labels, and demonstrates superior performance on benchmark datasets.

Contribution

The paper presents a novel multi-label classification model using interval type-2 fuzzy logic integrated with deep neural networks, enhancing label relationship modeling.

Findings

Outperforms baseline methods on benchmark datasets

Effectively models label relationships with fuzzy logic

Improves multi-label classification accuracy

Abstract

Prediction of multi-dimensional labels plays an important role in machine learning problems. We found that the classical binary labels could not reflect the contents and their relationships in an instance. Hence, we propose a multi-label classification model based on interval type-2 fuzzy logic. In the proposed model, we use a deep neural network to predict the type-1 fuzzy membership of an instance and another one to predict the fuzzifiers of the membership to generate interval type-2 fuzzy memberships. We also propose a loss function to measure the similarities between binary labels in datasets and interval type-2 fuzzy memberships generated by our model. The experiments validate that our approach outperforms baselines on multi-label classification benchmarks.