Mamba Meets Scheduling: Learning to Solve Flexible Job Shop Scheduling with Efficient Sequence Modeling

2026-02-24

AI Summary

This work addresses the challenge of efficiently modeling global dependencies between operations and machines in the flexible job shop scheduling problem (FJSP), where existing learning-based methods often fall short. To this end, we introduce the Mamba state space model—characterized by linear computational complexity—into FJSP for the first time. We propose a dual-branch Mamba encoder to separately capture sequential features of operations and machines, coupled with a lightweight cross-attention decoder to model their interactions for optimizing scheduling objectives such as makespan. Compared to conventional graph attention-based approaches, our method substantially reduces computational overhead while achieving faster solution times and superior performance across multiple FJSP benchmarks, outperforming current state-of-the-art learning-based scheduling algorithms.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Machine Learning: Learning with Manifolds
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as minimizing total completion time. Current learning-based methods in this domain often rely on localized feature extraction models, limiting their capacity to capture overarching dependencies spanning operations and machines. This paper introduces an innovative architecture that harnesses Mamba, a state-space model with linear computational complexity, to facilitate comprehensive sequence modeling tailored for FJSP. In contrast to prevalent graph-attention-based frameworks that are computationally intensive for FJSP, we show our model is more efficient. Specifically, the proposed model possesses an encoder and a decoder. The encoder incorporates a dual Mamba block to extract operation and machine features separately. Additionally, we introduce an efficient cross-attention decoder to learn interactive embeddings of operations and machines. Our experimental results demonstrate that our method achieves faster solving speed and surpasses the performance of state-of-the-art learning-based methods for FJSP across various benchmarks.

Problem

• Flexible Job Shop Scheduling
• Combinatorial Optimization
• Sequence Modeling
• Global Dependencies
• Manufacturing Scheduling

Innovation

• Mamba
• Flexible Job Shop Scheduling
• State-Space Model
• Sequence Modeling
• Cross-Attention Decoder