Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

7-2024

Abstract

Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attention network (TBGAT), a novel GNN architecture based on the attention mechanism, to embed the DG for solving JSSP in a local search framework. Specifically, TBGAT embeds the DG from a forward and a backward view, respectively, where the messages are propagated by following the different topologies of the views and aggregated via graph attention. Then, we propose a novel operator based on the message-passing mechanism to calculate the forward and backward topological sorts of the DG, which are the features for characterizing the topological structures and exploited by our model. In addition, we theoretically and experimentally show that TBGAT has linear computational complexity to the number of jobs and machines, respectively, strengthening our method's practical value. Besides, extensive experiments on five synthetic datasets and seven classic benchmarks show that TBGAT achieves new SOTA results by outperforming a wide range of neural methods by a large margin. All the code and data are publicly available online at https://github.com/zcaicaros/TBGAT.

Keywords

Data-driven optimization, deep reinforcement learning, job shop scheduling, graph neural network, neural heuristics

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence, Barcelona, Spain, 2024 July 15

First Page

1

Last Page

17

Publisher

UAI

City or Country

USA

Copyright Owner and License

Authors

Additional URL

https://www.auai.org/uai2024/accepted_papers

Download

Share

COinS