Learning Branching Heuristics from Graph Neural Networks

11/26/2022
by   Congsong Zhang, et al.
0

Backtracking has been widely used for solving problems in artificial intelligence (AI), including constraint satisfaction problems and combinatorial optimization problems. Good branching heuristics can efficiently improve the performance of backtracking by helping prune the search space and leading the search to the most promising direction. In this paper, we first propose a new graph neural network (GNN) model designed using the probabilistic method. From the GNN model, we introduce an approach to learn a branching heuristic for combinatorial optimization problems. In particular, our GNN model learns appropriate probability distributions on vertices in given graphs from which the branching heuristic is extracted and used in a backtracking search. Our experimental results for the (minimum) dominating-clique problem show that this learned branching heuristic performs better than the minimum-remaining-values heuristic in terms of the number of branches of the whole search tree. Our approach introduces a new way of applying GNNs towards enhancing the classical backtracking algorithm used in AI.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/22/2022

One Model, Any CSP: Graph Neural Networks as Fast Global Search Heuristics for Constraint Satisfaction

We propose a universal Graph Neural Network architecture which can be tr...
research
04/19/2023

Solving the Kidney-Exchange Problem via Graph Neural Networks with No Supervision

This paper introduces a new learning-based approach for approximately so...
research
03/24/2023

A Graph Neural Network Approach to Nanosatellite Task Scheduling: Insights into Learning Mixed-Integer Models

This study investigates how to schedule nanosatellite tasks more efficie...
research
06/05/2023

Barriers for the performance of graph neural networks (GNN) in discrete random structures. A comment on <cit.>,<cit.>,<cit.>

Recently graph neural network (GNN) based algorithms were proposed to so...
research
01/15/2014

Predicting the Performance of IDA* using Conditional Distributions

Korf, Reid, and Edelkamp introduced a formula to predict the number of n...
research
04/15/2020

Ants can orienteer a thief in their robbery

We address the Thief Orienteering Problem (ThOP), a multi-component prob...

Please sign up or login with your details

Forgot password? Click here to reset