Select Lab Publications


Distributed Parallel Inference on Large Factor Graphs (2009)

By: Joseph Gonzalez, Yucheng Low, Carlos Guestrin, and David O'Hallaron

Abstract:

As computer clusters become more common and the size of the problems encountered in the field of AI grows, there is an increasing demand for efficient parallel inference algorithms. We consider the problem of parallel inference on large factor graphs in the distributed memory setting of computer clusters. We develop a new efficient parallel inference algorithm, DBRSplash, which incorporates over-segmented graph partitioning, belief residual scheduling, and uniform work Splash operations. We empirically evaluate the DBRSplash algorithm on a 120 processor cluster and demonstrate linear to super-linear performance gains on large factor graph models.

Download Information
Joseph Gonzalez, Yucheng Low, Carlos Guestrin, and David O'Hallaron (2009). "Distributed Parallel Inference on Large Factor Graphs." Conference on Uncertainty in Artificial Intelligence (UAI). pdf   talk      
BibTeX citation

@inproceedings{Gonzalez+al:uai09paraml,
title = {Distributed Parallel Inference on Large Factor Graphs},
author = {Joseph Gonzalez and Yucheng Low and Carlos Guestrin and David O'Hallaron},
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
month = {July},
year = {2009},
address = {Montreal, Canada},
wwwfilebase = {uai2009-gonzalez-low-guestrin-ohallaron},
wwwtopic = {Parallel Learning},
}



full list