Belief Propagation Neural Networks

07/01/2020
by   Jonathan Kuck, et al.
Shanghai Jiao Tong University
Stanford University
Allen Institute for Artificial Intelligence
14

Learned neural solvers have successfully been used to solve combinatorial optimization and decision problems. More general counting variants of these problems, however, are still largely solved with hand-crafted solvers. To bridge this gap, we introduce belief propagation neural networks (BPNNs), a class of parameterized operators that operate on factor graphs and generalize Belief Propagation (BP). In its strictest form, a BPNN layer (BPNN-D) is a learned iterative operator that provably maintains many of the desirable properties of BP for any choice of the parameters. Empirically, we show that by training BPNN-D learns to perform the task better than the original BP: it converges 1.7x faster on Ising models while providing tighter bounds. On challenging model counting problems, BPNNs compute estimates 100's of times faster than state-of-the-art handcrafted methods, while returning an estimate of comparable quality.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/09/2012

Counting Belief Propagation

A major benefit of graphical models is that most knowledge is captured i...
12/30/2016

Shape Estimation from Defocus Cue for Microscopy Images via Belief Propagation

In recent years, the usefulness of 3D shape estimation is being realized...
03/08/2023

DNBP: Differentiable Nonparametric Belief Propagation

We present a differentiable approach to learn the probabilistic factors ...
01/15/2021

Differentiable Nonparametric Belief Propagation

We present a differentiable approach to learn the probabilistic factors ...
04/05/2022

Nonlocal optimization of binary neural networks

We explore training Binary Neural Networks (BNNs) as a discrete variable...
06/07/2017

Improving Max-Sum through Decimation to Solve Loopy Distributed Constraint Optimization Problems

In the context of solving large distributed constraint optimization prob...
12/20/2019

When Explanations Lie: Why Modified BP Attribution Fails

Modified backpropagation methods are a popular group of attribution meth...

Please sign up or login with your details

Forgot password? Click here to reset