Probing neural combinatorial optimization models
Publication Type
Conference Proceeding Article
Publication Date
12-2025
Abstract
Neural combinatorial optimization (NCO) has achieved remarkable performance, yet its learned model representations and decision rationale remain a black box. This impedes both academic research and practical deployment, since researchers and stakeholders require deeper insights into NCO models. In this paper, we take the first critical step towards interpreting NCO models by investigating their representations through various probing tasks. Moreover, we introduce a novel probing tool named Coefficient Significance Probing (CS-Probing) to enable deeper analysis of NCO representations by examining the coefficients and statistical significance during probing. Extensive experiments and analysis reveal that NCO models encode low-level information essential for solution construction, while capturing high-level knowledge to facilitate better decisions. Using CS-Probing, we find that prevalent NCO models impose varying inductive biases on their learned representations, uncover direct evidence related to model generalization, and identify key embedding dimensions associated with specific knowledge. These insights can be potentially translated into practice, for example, with minor code modifications, we improve the generalization of the analyzed model. Our work represents a first systematic attempt to interpret black-box NCO models, showcasing probing as a promising tool for analyzing their internal mechanisms and revealing insights for the NCO community. The source code is publicly available.
Discipline
Artificial Intelligence and Robotics
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 39th Conference on Neural Information Processing, San Diego, California, December 2-7
First Page
1
Last Page
39
Identifier
10.48550/arXiv.2510.22131
City or Country
San Diego, US
Citation
ZHANG, Zhiqin; MA, Yining; CAO, Zhiguang; and LAU, Hoong Chuin.
Probing neural combinatorial optimization models. (2025). Proceedings of the 39th Conference on Neural Information Processing, San Diego, California, December 2-7. 1-39.
Available at: https://ink.library.smu.edu.sg/sis_research/10577
Additional URL
https://doi.org/10.48550/arXiv.2510.22131