Rigorous Explanation of Inference on Probabilistic Graphical Models

04/21/2020
by   Yifei Liu, et al.
0

Probabilistic graphical models, such as Markov random fields (MRF), exploit dependencies among random variables to model a rich family of joint probability distributions. Sophisticated inference algorithms, such as belief propagation (BP), can effectively compute the marginal posteriors. Nonetheless, it is still difficult to interpret the inference outcomes for important human decision making. There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models. Shapley values provide an axiomatic framework, but naively computing or even approximating the values on general graphical models is challenging and less studied. We propose GraphShapley to integrate the decomposability of Shapley values, the structure of MRFs, and the iterative nature of BP inference in a principled way for fast Shapley value computation, that 1) systematically enumerates the important contributions to the Shapley values of the explaining variables without duplicate; 2) incrementally compute the contributions without starting from scratches. We theoretically characterize GraphShapley regarding independence, equal contribution, and additivity. On nine graphs, we demonstrate that GraphShapley provides sensible and practical explanations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/20/2012

Accuracy Bounds for Belief Propagation

The belief propagation (BP) algorithm is widely applied to perform appro...
research
07/20/2011

Finding Non-overlapping Clusters for Generalized Inference Over Graphical Models

Graphical models use graphs to compactly capture stochastic dependencies...
research
11/09/2018

Block Belief Propagation for Parameter Learning in Markov Random Fields

Traditional learning methods for training Markov random fields require d...
research
01/20/2012

Dynamic Decision Making for Graphical Models Applied to Oil Exploration

This paper has been withdrawn by the authors. We present a framework for...
research
12/06/2021

Graphical Models with Attention for Context-Specific Independence and an Application to Perceptual Grouping

Discrete undirected graphical models, also known as Markov Random Fields...
research
02/14/2023

Joint Probability Trees

We introduce Joint Probability Trees (JPT), a novel approach that makes ...
research
08/13/2019

Scalable Explanation of Inferences on Large Graphs

Probabilistic inferences distill knowledge from graphs to aid human make...

Please sign up or login with your details

Forgot password? Click here to reset