Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data

02/23/2017
by   Sigurd Løkse, et al.
0

In this paper, we propose PCKID, a novel, robust, kernel function for spectral clustering, specifically designed to handle incomplete data. By combining posterior distributions of Gaussian Mixture Models for incomplete data on different scales, we are able to learn a kernel for incomplete data that does not depend on any critical hyperparameters, unlike the commonly used RBF kernel. To evaluate our method, we perform experiments on two real datasets. PCKID outperforms the baseline methods for all fractions of missing values and in some cases outperforms the baseline methods with up to 25 percentage points.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2020

Spectral clustering via adaptive layer aggregation for multi-layer networks

One of the fundamental problems in network analysis is detecting communi...
research
12/16/2019

A Robust Spectral Clustering Algorithm for Sub-Gaussian Mixture Models with Outliers

We consider the problem of clustering datasets in the presence of arbitr...
research
05/03/2015

Kernel Spectral Clustering and applications

In this chapter we review the main literature related to kernel spectral...
research
09/07/2019

Concentration of kernel matrices with application to kernel spectral clustering

We study the concentration of random kernel matrices around their mean. ...
research
07/10/2019

Time series cluster kernels to exploit informative missingness and incomplete label information

The time series cluster kernel (TCK) provides a powerful tool for analys...
research
10/26/2017

Energy Clustering

Energy statistics was proposed by Székely in the 80's inspired by the Ne...
research
10/17/2019

A Unified Framework for Tuning Hyperparameters in Clustering Problems

Selecting hyperparameters for unsupervised learning problems is difficul...

Please sign up or login with your details

Forgot password? Click here to reset