The orbital angular momentum for an atomic electron can be visualized in terms of a vector model where the angular momentum vector is seen as precessing about a direction in space. While the angular momentum vector has the magnitude shown, only a maximum of l units can be measured along a given direction, where l is the orbital quantum number . Each of the four vector representations is an isomorphism, so the inverse linear transformation could be depicted with an arrow pointing in the other direction. The four vector spaces across the bottom are familiar from the earliest days of the course, while the four vector spaces across the top are completely abstract.
Incontrast,representation learning approaches treat this problem as machine learning task itself, using a data-driven approach to learn embeddings that encode graph structure. Here we provide an overview of recent advancements in representation learning on graphs, reviewing tech-niques for representing both nodes and entire subgraphs.