ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

Yeqing Qiu; Ye XUE; Akang Wang; Yiheng Wang; Qingjiang Shi; Zhi-Quan Luo

2025 ICML ICML 2025

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-k-Cut Problems

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Knowledge & Reasoning

Authors

Yeqing Qiu, Ye XUE, Akang Wang, Yiheng Wang, Qingjiang Shi, Zhi-Quan Luo

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Graph Neural Networks Knowledge & Reasoning > Representation > Knowledge Graphs

Keywords

graph neural network fine-tune continuous solution max-$k$-cut pre-train sampling-based construction

Download PDF