Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2025

Abstract

Recent decomposition-based neural multi-objective combinatorial optimization (MOCO) methods struggle to achieve desirable performance. Even equipped with complex learning techniques, they often suffer from significant optimality gaps in weight-specific subproblems. To address this challenge, we propose a neat weight embedding method to learn weight-specific representations, which captures weight-instance interaction for the subproblems and was overlooked by most current methods. We demonstrate the potentials of our method in two instantiations. First, we introduce a succinct addition model to learn weight-specific node embeddings, which surpassed most existing neural methods. Second, we design an enhanced conditional attention model to simultaneously learn the weight embedding and node embeddings, which yielded new state-of-the-art performance. Experimental results on classic MOCO problems verified the superiority of our method. Remarkably, our method also exhibits favorable generalization performance across problem sizes, even outperforming the neural method specialized for boosting size generalization.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Sustainability

Publication

Proceedings of the 13th International Conference on Learning Representations, Singapore, 2025 April 24

First Page

39396

Last Page

39415

ISBN

9798331320850

Publisher

ICLR

City or Country

Singapore

Additional URL

https://openreview.net/forum?id=GM7cmQfk2F

Download

Share

COinS