Journal article · 2026 · Open access

ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem

Peixiang Wang, Hongye Zhao, Wei Qin, Heng Huang, Dong Xu

IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15 · Published 12 November 2026 · DOI 10.1109/tnnls.2026.3746045

Open full textCite this paper

In brief

“ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem” is a 2026 journal article by Peixiang Wang and 4 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.

Citations
0
Authors
5

Abstract

In modern maritime logistics, driven by the strategic imperative to reduce carbon emissions, enhancing the operational efficiency of container terminals is of paramount importance. A primary obstacle is the container relocation problem (CRP), a unique, nonproductive operation where the goal is to minimize unnecessary container moves. Unlike simpler packing or allocation problems, the CRP is governed by retrieval-order and blocking constraints, which make it a challenging sequential combinatorial optimization problem (COP). As a classic and critical NP-hard problem, efficiently reducing these relocations presents a significant challenge. To address this, we propose the attention-based ranking and contrastive learning network (ARCNet), a learning framework that embeds operations research (OR) theory into a deep learning model featuring graph attention networks (GATs) and a Transformer. We use contrastive learning to instill OR insights, allowing the model to understand how optimal strategies adapt to different problem structures. Furthermore, a curriculum learning approach enables generalization from small, solved instances to large-scale scenarios. This strategy is crucial as it allows the model to learn effective policies even in the absence of optimal solutions for large-scale problems. Experiments show that ARCNet achieves near-optimal results and, with a predictive enhancement, significantly outperforms existing heuristics.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, P., Zhao, H., Qin, W., Huang, H., & Xu, D. (2026). ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3746045

MLA 9

Wang, Peixiang, et al. “ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem.” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tnnls.2026.3746045.

Chicago

Wang, Peixiang, Hongye Zhao, Wei Qin, Heng Huang, and Dong Xu. 2026. “ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem.” IEEE Transactions on Neural Networks and Learning Systems PP: 1–15. https://doi.org/10.1109/tnnls.2026.3746045.

Harvard

Wang, P. et al. (2026) ‘ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem’, IEEE Transactions on Neural Networks and Learning Systems, PP, pp. 1–15. doi:10.1109/tnnls.2026.3746045.

IEEE

P. Wang, H. Zhao, W. Qin, H. Huang, and D. Xu, “ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, pp. 1–15, 2026, doi: 10.1109/tnnls.2026.3746045.

BibTeX

@article{wang2026arcnet,
  title     = {{ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem}},
  author    = {Wang, Peixiang and Zhao, Hongye and Qin, Wei and Huang, Heng and Xu, Dong},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2026},
  volume    = {PP},
  pages     = {1--15},
  doi       = {10.1109/tnnls.2026.3746045},
  url       = {https://doi.org/10.1109/tnnls.2026.3746045}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Maritime Ports and Logistics

  • container relocation problem
  • container terminals
  • maritime logistics
  • graph attention networks
  • transformer models
  • contrastive learning
  • curriculum learning
  • combinatorial optimization

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Wang, P., Zhao, H., Qin, W., Huang, H., & Xu, D. (2026). ARCNet: Embedding Operations Research Insights Into an Attention-Based Ranking and Contrastive Learning Framework for the Container Relocation Problem. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3746045

How many times has this paper been cited?

0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.

Who wrote this paper?

Peixiang Wang, Hongye Zhao, Wei Qin, Heng Huang, Dong Xu.

What is the DOI of this paper?

10.1109/tnnls.2026.3746045, permanently at https://doi.org/10.1109/tnnls.2026.3746045. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.