Select Lab Publications


Efficient Probabilistic Inference with Partial Ranking Queries (2011)

By: Jonathan Huang, Ashish Kapoor, and Carlos Guestrin

Abstract: Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, typically forces one to make structural assumptions, such as smoothness, sparsity, or probabilistic independence about these underlying distributions. We approach the modeling problem from the computational principle that one should make structural assumptions which allow for efficient calculation of typical probabilistic queries. For ranking models, ``typical'' queries predominantly take the form of partial ranking queries (e.g., given a user's top-k favorite movies, what are his preferences over remaining movies?). In this paper, we argue that riffled independence factorizations proposed in recent literature (Huang et al., '09, '10) are a natural structural assumption for ranking distributions, allowing for particularly efficient processing of partial ranking queries.



Download Information
Jonathan Huang, Ashish Kapoor, and Carlos Guestrin (2011). "Efficient Probabilistic Inference with Partial Ranking Queries." The 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011). pdf long   poster  
BibTeX citation

@inproceedings{Huang+al:uai11prank,
title = {Efficient Probabilistic Inference with Partial Ranking Queries},
author = {Jonathan Huang and Ashish Kapoor and Carlos Guestrin},
booktitle = {The 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011)},
month = {July},
year = {2011},
address = {Barcelona, Spain},
wwwfilebase = {uai2011-huang-kapoor-guestrin},
wwwtopic = {Permutations}
}



full list