arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11995cs.LGcs.NE
收藏

一种用于图神经网络超参数优化的树型变异遗传算法

A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks

Heriot-Watt University(赫瑞-瓦特大学)

Yingfang Yuan, Wenjun Wang, Wei Pang

摘要:

近年来,图神经网络(GNNs)由于具有处理图相关问题的优异能力而受到越来越多的关注。在实践中,超参数优化(HPO)对于GNN实现令人满意的结果至关重要,但这个过程成本很高,因为不同超参数设置的评估需要过度训练许多GNN。已经提出了许多方法HPO,其目的是有效地识别有前途的超参数。特别地,已经探索了用于HPO的遗传算法(GA),其将GNN视为黑盒模型,给定一组超参数,只能观察其输出。然而,由于GNN模型非常复杂,并且对GNN上的超参数进行评估非常昂贵,因此GA需要先进的技术来平衡搜索的探索和利用,并在有限的计算资源下使优化更加有效。因此,我们提出了一个树结构的变异策略,遗传算法来缓解这个问题。同时,我们回顾了HPO的最新研究成果,为树结构的思想提供了发展的空间,希望我们的方法能在未来进一步完善这些HPO方法。

英文摘要:

In recent years, graph neural networks (GNNs) have gained increasing attention, as they possess the excellent capability of processing graph-related problems. In practice, hyperparameter optimisation (HPO) is critical for GNNs to achieve satisfactory results, but this process is costly because the evaluations of different hyperparameter settings require excessively training many GNNs. Many approaches have been proposed for HPO, which aims to identify promising hyperparameters efficiently. In particular, the genetic algorithm (GA) for HPO has been explored, which treats GNNs as a black-box model, of which only the outputs can be observed given a set of hyperparameters. However, because GNN models are sophisticated and the evaluations of hyperparameters on GNNs are expensive, GA requires advanced techniques to balance the exploration and exploitation of the search and make the optimisation more effective given limited computational resources. Therefore, we proposed a tree-structured mutation strategy for GA to alleviate this issue. Meanwhile, we reviewed the recent HPO works, which gives room for the idea of tree-structure to develop, and we hope our approach can further improve these HPO methods in the future.

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。

↑