Many graph data management approaches are unsuitable for large-scale, complex-pattern and frequently updating knowledge graphs. Their complex patterns make the access mode of knowledge graphs more complicated than that of relational data. Knowledge Graph Access Structure Selection Based on Machine Learning offers important steps in machine-learning-based knowledge graph access structure selection, including performance prediction of storage structure, automatic storage structure tuning, automatic storage structure design, automatic index selection, and automatic query prediction, introducing solutions for each. It implements an automatic knowledge graph access structure selection system based on reinforcement learning, verifying the suitability, effectiveness and availability of the proposed solutions.• Presents state-of-the-art machine-learning-based techniques to knowledge graph access structures.• Offers valuable takeaway suggestions on knowledge graph access structure selection.• Opens promising avenues for the further study of knowledge graph data management.