Dirichlet Process Mixtures of Generalized Mallows Models
This work addresses clustering challenges in ranked data analysis, but it is incremental as it builds on existing Dirichlet process and Mallows model frameworks.
The paper tackled the problem of clustering discrete incomplete rankings by introducing a Dirichlet process mixture model and two Gibbs sampling inference techniques, demonstrating improved convergence and benefits over alternative methods for large real-world datasets.
We present a Dirichlet process mixture model over discrete incomplete rankings and study two Gibbs sampling inference techniques for estimating posterior clusterings. The first approach uses a slice sampling subcomponent for estimating cluster parameters. The second approach marginalizes out several cluster parameters by taking advantage of approximations to the conditional posteriors. We empirically demonstrate (1) the effectiveness of this approximation for improving convergence, (2) the benefits of the Dirichlet process model over alternative clustering techniques for ranked data, and (3) the applicability of the approach to exploring large realworld ranking datasets.