Graph embeddings is a research area in machine learning and network analysis that focuses on representing graph structures in a lower-dimensional vector space. The goal of graph embeddings is to capture the inherent relationships and properties of nodes and edges in a graph in a more compact and learnable form. This allows for easier analysis, visualization, and machine learning tasks on graph data. Graph embeddings methods can be unsupervised, semi-supervised, or supervised, and can be applied to various tasks such as network representation learning, node classification, link prediction, and community detection.