图神经网络超参数优化用于分子性质预测的系统比较研究
A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction
摘要：
图神经网络（GNN）已经被提出用于广泛的图相关学习任务。特别是近年来，越来越多的GNN系统被应用于预测分子性质。然而，一个直接的障碍是选择合适的超参数，以实现令人满意的性能，较低的计算成本。与此同时，在典型的深度学习应用中，许多分子数据集远远小于许多其他数据集。大多数超参数优化（HPO）方法尚未在分子域中的小数据集上探索其效率。在本文中，我们进行了理论分析的共同和特殊功能的两个国家的最先进的和流行的算法HPO：TPE和CMA-ES，我们比较了它们与随机搜索（RS），这是作为一个基线。在MoleculeNet平台上，从不同的角度对RS、TPE和CMA-ES对GNNs的HPO影响进行了实验研究，以预测GNNs的分子性质。在我们的实验中，我们得出结论，RS，TPE和CMA-ES在解决不同的特定分子问题时具有各自的优势。最后，我们相信我们的工作将激励GNN应用于化学和材料科学中的分子机器学习问题的进一步研究。
英文摘要：
Graph neural networks (GNNs) have been proposed for a wide range of graph-related learning tasks. In particular, in recent years, an increasing number of GNN systems were applied to predict molecular properties. However, a direct impediment is to select appropriate hyperparameters to achieve satisfactory performance with lower computational cost. Meanwhile, many molecular datasets are far smaller than many other datasets in typical deep learning applications. Most hyperparameter optimization (HPO) methods have not been explored in terms of their efficiencies on such small datasets in the molecular domain. In this paper, we conducted a theoretical analysis of common and specific features for two state-of-the-art and popular algorithms for HPO: TPE and CMA-ES, and we compared them with random search (RS), which is used as a baseline. Experimental studies are carried out on several benchmarks in MoleculeNet, from different perspectives to investigate the impact of RS, TPE, and CMA-ES on HPO of GNNs for molecular property prediction. In our experiments, we concluded that RS, TPE, and CMA-ES have their individual advantages in tackling different specific molecular problems. Finally, we believe our work will motivate further research on GNN as applied to molecular machine learning problems in chemistry and materials sciences.
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。
