Performance Evaluation Of Prediction On Molecular Graphs With Graph Neural Networks

Abstract

AO_SCPLOWBSTRACTC_SCPLOWMachine learning and deep learning are novel and trending approaches to solving real-world scientific problems. Graph machine learning is dedicated to performing learning methods, such as graph neural networks, on non-Euclidean data such as graphs. Molecules, with their natural graph structures, could be analyzed by such method. In this work, we carry out the performance evaluation regarding to learning results as well as time consumed, speedup, and efficiency using different types of neural network structures and distributed training pipeline implementations. Besides, the reasons lead to an unideal performance enhancement is investigated. Code availability at https://github.com/htlee6/perf-analysis-dist-training-gnn.