Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation
This addresses the challenge for data analysts in exploring datasets where domain-specific clustering criteria are hard to formalize, offering an incremental improvement in interactive clustering tools.
The paper tackles the problem of interactive clustering for data exploration by introducing TINDER, a method that allows analysts to reject clusterings and request new ones, resulting in a diverse set of clusterings of equivalent quality, with much greater diversity than randomized restarts.
A good clustering can help a data analyst to explore and understand a data set, but what constitutes a good clustering may depend on domain-specific and application-specific criteria. These criteria can be difficult to formalize, even when it is easy for an analyst to know a good clustering when they see one. We present a new approach to interactive clustering for data exploration called TINDER, based on a particularly simple feedback mechanism, in which an analyst can reject a given clustering and request a new one, which is chosen to be different from the previous clustering while fitting the data well. We formalize this interaction in a Bayesian framework as a method for prior elicitation, in which each different clustering is produced by a prior distribution that is modified to discourage previously rejected clusterings. We show that TINDER successfully produces a diverse set of clusterings, each of equivalent quality, that are much more diverse than would be obtained by randomized restarts.