Pretrained Cost Model for Distributed Constraint Optimization Problems

Authors

  • Yanchen Deng School of Computer Science and Engineering, Nanyang Technological University
  • Shufeng Kong School of Computer Science and Engineering, Nanyang technological university
  • Bo An School of Computer Science and Engineering, Nanyang Technological University

DOI:

https://doi.org/10.1609/aaai.v36i9.21164

Keywords:

Multiagent Systems (MAS), Constraint Satisfaction And Optimization (CSO), Knowledge Representation And Reasoning (KRR), Search And Optimization (SO)

Abstract

Distributed Constraint Optimization Problems (DCOPs) are an important subclass of combinatorial optimization problems, where information and controls are distributed among multiple autonomous agents. Previously, Machine Learning (ML) has been largely applied to solve combinatorial optimization problems by learning effective heuristics. However, existing ML-based heuristic methods are often not generalizable to different search algorithms. Most importantly, these methods usually require full knowledge about the problems to be solved, which are not suitable for distributed settings where centralization is not realistic due to geographical limitations or privacy concerns. To address the generality issue, we propose a novel directed acyclic graph representation schema for DCOPs and leverage the Graph Attention Networks (GATs) to embed graph representations. Our model, GAT-PCM, is then pretrained with optimally labelled data in an offline manner, so as to construct effective heuristics to boost a broad range of DCOP algorithms where evaluating the quality of a partial assignment is critical, such as local search or backtracking search. Furthermore, to enable decentralized model inference, we propose a distributed embedding schema of GAT-PCM where each agent exchanges only embedded vectors, and show its soundness and complexity. Finally, we demonstrate the effectiveness of our model by combining it with a local search or a backtracking search algorithm. Extensive empirical evaluations indicate that the GAT-PCM-boosted algorithms significantly outperform the state-of-the-art methods in various benchmarks.

Downloads

Published

2022-06-28

How to Cite

Deng, Y., Kong, S., & An, B. (2022). Pretrained Cost Model for Distributed Constraint Optimization Problems. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 9331-9340. https://doi.org/10.1609/aaai.v36i9.21164

Issue

Section

AAAI Technical Track on Multiagent Systems