Learning Topological Representations with Bidirectional Graph Attention Network for Solving Job Shop Scheduling Problem

TL;DR

This paper introduces TBGAT, a novel topologically-aware graph attention network that effectively captures disjunctive graph structures for job shop scheduling, achieving state-of-the-art results with linear complexity.

Contribution

The paper proposes TBGAT, a bidirectional graph attention network that embeds disjunctive graphs from forward and backward views for improved job shop scheduling.

Findings

TBGAT outperforms existing neural methods on multiple benchmarks.

The model has linear computational complexity relative to jobs and machines.

Extensive experiments validate the effectiveness of the proposed approach.

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.