Repository of the paper "Community Detection Methods for Multi-Label Classification" publish in BRACIS 2023

This repository hold all experiments conducted during my PhD (2019-2023). HPML means "Hybrid Partitions for Multi-Label Classification". SET-UP-1

BT-MA is a Multi-label Machine learning model

This code is part of my PhD research. This code select the best partition using the CLUS framework. We choose the partition with the best Macro-F1.

This code is part of my PhD research. This code select the best partition using the silhouete coefficient.

This code is part of my doctoral research. The aim is to generate a specific version of random partitions for multilabel classification.

This code is part of my doctoral research. The aim is to generate a specific version of random partitions for multilabel classification.

This code is part of my doctoral research. The aim is test the best hybrid partitions chosen with silhouette coefficient. But here we using a chain of hybrid partitions to do the test.

This code is part of my Ph.D. research. This code selects the best partition using the CLUS framework. We choose the partition with the best Micro-F1.

This code is part of my Ph.D. research. Test the best hybrid partition chosen with Micro-F1 criteria using Clus framework.

This code is part of my doctoral research. The aim is to generate partitions from the Jaccard index for multilabel classification.

This code is part of my PhD research. This code generate hybrid partitions using Kohonen to modeling the labels correlations, and HClust to partitioning the label space.

This code is part of my doctoral research. The aim is to generate a specific version of random partitions for multilabel classification.