Recent Trends in Correlation Clustering

The existing numeric data clustering algorithms are found limited to clustering based on the representation of data objects to be clustered. The pair wise relationships between any two data points were found to have existed in what is called Categorical data. This brought to a variety of categorical data clustering techniques. The issues left unresolved then included handling high dimensionality of data and the multiple relations data points can have with each other instead of only pair wise relationships. This brought to the Correlation clustering technique with different correlations in different clusters. This paper discusses the same and surveys the recent developments in the Correlation clustering.