Non-parametric domain approximation for scalable Gibbs sampling in MLNs


MLNs utilize relational structures that are ubiquitous in real-world situations to represent large probabilistic graphical models compactly. However, as is now well-known, inference complexity is one of the main bottlenecks in MLNs. Recently, several approaches have been proposed that exploit approximate symmetries in the MLN to reduce inference complexity. These approaches approximate large domains containing many objects with much smaller domains of meta-objects (or cluster-centers), so that inference is considerably faster and more scalable. However, a drawback in most of these approaches is that it is typically very hard to tune the parameters (e.g., number of clusters) such that inference is both efficient and accurate. Here, we propose a novel non-parametric approach that trades-off solution quality with efficiency to automatically learn the optimal domain approximation. Further, we show how to perform Gibbs sampling effectively in a domainapproximated MLN by adapting the sampler according to the approximation. Our results on several benchmarks show that our approach is scalable, accurate and converges faster than existing methods.

Publication Title

32nd Conference on Uncertainty in Artificial Intelligence 2016, UAI 2016

This document is currently not available here.