Equivariant Neural Network for Factor Graphs

09/29/2021
by   Fan-Yun Sun, et al.
12

Several indices used in a factor graph data structure can be permuted without changing the underlying probability distribution. An algorithm that performs inference on a factor graph should ideally be equivariant or invariant to permutations of global indices of nodes, variable orderings within a factor, and variable assignment orderings. However, existing neural network-based inference procedures fail to take advantage of this inductive bias. In this paper, we precisely characterize these isomorphic properties of factor graphs and propose two inference models: Factor-Equivariant Neural Belief Propagation (FE-NBP) and Factor-Equivariant Graph Neural Networks (FE-GNN). FE-NBP is a neural network that generalizes BP and respects each of the above properties of factor graphs while FE-GNN is an expressive GNN model that relaxes an isomorphic property in favor of greater expressivity. Empirically, we demonstrate on both real-world and synthetic datasets, for both marginal inference and MAP inference, that FE-NBP and FE-GNN together cover a range of sample complexity regimes: FE-NBP achieves state-of-the-art performance on small datasets while FE-GNN achieves state-of-the-art performance on large datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2021

Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

We focus on graph classification using a graph neural network (GNN) mode...
research
03/04/2020

Neural Enhanced Belief Propagation on Factor Graphs

A graphical model is a structured representation of locally dependent ra...
research
02/27/2022

Distribution Preserving Graph Representation Learning

Graph neural network (GNN) is effective to model graphs for distributed ...
research
01/23/2019

Constant Time Graph Neural Networks

Recent advancements in graph neural networks (GNN) have led to state-of-...
research
08/19/2020

Training Sensitivity in Graph Isomorphism Network

Graph neural network (GNN) is a popular tool to learn the lower-dimensio...
research
07/26/2022

ScoreCAM GNN: une explication optimale des réseaux profonds sur graphes

The explainability of deep networks is becoming a central issue in the d...
research
05/27/2022

Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation

In general, to draw robust conclusions from a dataset, all the analyzed ...

Please sign up or login with your details

Forgot password? Click here to reset