Generalized Collective Inference with Symmetric Clique Potentials

07/03/2009
by   Rahul Gupta, et al.
0

Collective graphical models exploit inter-instance associative dependence to output more accurate labelings. However existing models support very limited kind of associativity which restricts accuracy gains. This paper makes two major contributions. First, we propose a general collective inference framework that biases data instances to agree on a set of properties of their labelings. Agreement is encouraged through symmetric clique potentials. We show that rich properties leads to bigger gains, and present a systematic inference procedure for a large class of such properties. The procedure performs message passing on the cluster graph, where property-aware messages are computed with cluster specific algorithms. This provides an inference-only solution for domain adaptation. Our experiments on bibliographic information extraction illustrate significant test error reduction over unseen domains. Our second major contribution consists of algorithms for computing outgoing messages from clique clusters with symmetric clique potentials. Our algorithms are exact for arbitrary symmetric potentials on binary labels and for max-like and majority-like potentials on multiple labels. For majority potentials, we also provide an efficient Lagrangian Relaxation based algorithm that compares favorably with the exact algorithm. We present a 13/15-approximation algorithm for the NP-hard Potts potential, with runtime sub-quadratic in the clique size. In contrast, the best known previous guarantee for graphs with Potts potentials is only 1/2. We empirically show that our method for Potts potentials is an order of magnitude faster than the best alternatives, and our Lagrangian Relaxation based algorithm for majority potentials beats the best applicable heuristic -- ICM.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/23/2013

A General Algorithm for Approximate Inference and its Application to Hybrid Bayes Nets

The clique tree algorithm is the standard method for doing inference in ...
research
07/05/2015

Parsimonious Labeling

We propose a new family of discrete energy minimization problems, which ...
research
06/06/2021

Graph Belief Propagation Networks

With the wide-spread availability of complex relational data, semi-super...
research
06/06/2015

Deeply Learning the Messages in Message Passing Inference

Deep structured output learning shows great promise in tasks like semant...
research
01/15/2015

Submodular relaxation for inference in Markov random fields

In this paper we address the problem of finding the most probable state ...
research
06/01/2023

Approximate inference of marginals using the IBIA framework

Exact inference of marginals in probabilistic graphical models (PGM) is ...

Please sign up or login with your details

Forgot password? Click here to reset