Application of Graph Neural Networks and graph descriptors for graph classification
This work addresses the need for robust evaluation in graph classification, particularly for applications in chemistry and drug discovery, though it is incremental in nature.
The thesis tackled graph classification by evaluating Graph Neural Networks (GNNs) and classical methods like graph descriptors, establishing a fair experimental protocol and datasets to analyze performance. It found that the Jumping Knowledge GNN architecture efficiently improves base models, with multiple verified enhancements contributing to fair model comparison.
Graph classification is an important area in both modern research and industry. Multiple applications, especially in chemistry and novel drug discovery, encourage rapid development of machine learning models in this area. To keep up with the pace of new research, proper experimental design, fair evaluation, and independent benchmarks are essential. Design of strong baselines is an indispensable element of such works. In this thesis, we explore multiple approaches to graph classification. We focus on Graph Neural Networks (GNNs), which emerged as a de facto standard deep learning technique for graph representation learning. Classical approaches, such as graph descriptors and molecular fingerprints, are also addressed. We design fair evaluation experimental protocol and choose proper datasets collection. This allows us to perform numerous experiments and rigorously analyze modern approaches. We arrive to many conclusions, which shed new light on performance and quality of novel algorithms. We investigate application of Jumping Knowledge GNN architecture to graph classification, which proves to be an efficient tool for improving base graph neural network architectures. Multiple improvements to baseline models are also proposed and experimentally verified, which constitutes an important contribution to the field of fair model comparison.