zsk66 / fmeans

f-means

Introduction

This repo holds the source code and scripts for reproducing the key experiments of our paper: Scalable Two-Stage Algorithm for Achieving Individual Fairness in k-means Clustering.

Datasets

We give four datasets here: bank, census, creditcard and diabetes with 1000 samples. For more datasets, you could download from the following repositories, and process them into .mat format.

Dataset	link	Dimension
Covtype	https://archive.ics.uci.edu/ml/datasets/covertype	54
KDD	https://osmot.cs.cornell.edu/kddcup/datasets.html	74
3D-spatial-network	https://archive.ics.uci.edu/ml/datasets/3D+Road+Network+%28North+Jutland%2C+Denmark%29	3
urbanGB	https://archive.ics.uci.edu/ml/datasets/UrbanGB%2C+urban+road+accidents+coordinates+labelled+by+the+urban+center	2
NYC-Taxi	https://drive.google.com/open?id=1CH_FPB4deDVFm_zDvyya5YMbFBOOz7Bn	2
t-drive	http://www.cs.cornell.edu/~wenleix/paper/tdrive.pdf	2

Start

run main.m 

Authors

• Sheng Wang
• Shengkun Zhu
• Songsong Mo
• Yuan Sun