arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.05054cs.LGcs.DC
收藏

图神经网络作为并行图着色的排序启发式方法

Graph Neural Networks as Ordering Heuristics for Parallel Graph Coloring

University of Bergen(卑尔根大学)

Kenneth Langedal, Fredrik Manne

AI总结:

本文提出一种基于 GNN 的并行图着色排序启发式方法,结合监督与无监督训练,在着色质量、运行时间和并行扩展性上优于 LF 与 SL。

摘要:

图着色问题要求为无向图中的顶点分配最少数量的不同颜色,并满足任意一对相邻顶点不能共享相同颜色的约束。该问题是一个得到充分研究的 NP-hard 组合优化问题,具有多种实际应用。因此,已有许多贪心启发式方法被提出,在着色质量、执行时间以及并行可扩展性之间取得良好平衡。在本工作中,我们引入一种基于图神经网络(GNN)的排序启发式方法,并证明其在质量和性能上均优于现有贪心排序启发式方法。此前结果已经表明,GNN 能够生成高质量着色,但代价是运行时间过长。本文首次将执行时间降低到可与现有贪心启发式方法竞争的水平。我们的 GNN 模型同时使用监督和无监督技术进行训练。实验结果表明,一个 2 层 GNN 模型的执行时间介于最大度优先(LF)和最小度置后(SL)排序启发式方法之间,同时在着色质量上优于二者。增加层数会进一步提升着色质量,并且只有在四层时,SL 才会比 GNN 更快。最后,与 SL 和 LF 相比,我们基于 GNN 的着色启发式方法在并行设置下实现了更优的扩展性。

英文摘要:

The graph coloring problem asks for an assignment of the minimum number of distinct colors to vertices in an undirected graph with the constraint that no pair of adjacent vertices share the same color. The problem is a thoroughly studied NP-hard combinatorial problem with several real-world applications. As such, a number of greedy heuristics have been suggested that strike a good balance between coloring quality, execution time, and also parallel scalability. In this work, we introduce a graph neural network (GNN) based ordering heuristic and demonstrate that it outperforms existing greedy ordering heuristics both on quality and performance. Previous results have demonstrated that GNNs can produce high-quality colorings but at the expense of excessive running time. The current paper is the first that brings the execution time down to compete with existing greedy heuristics. Our GNN model is trained using both supervised and unsupervised techniques. The experimental results show that a 2-layer GNN model can achieve execution times between the largest degree first (LF) and smallest degree last (SL) ordering heuristics while outperforming both on coloring quality. Increasing the number of layers improves the coloring quality further, and it is only at four layers that SL becomes faster than the GNN. Finally, our GNN-based coloring heuristic achieves superior scaling in the parallel setting compared to both SL and LF.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑