Edge-level learning
Edge-level learning is a branch of graph ML that focuses on predicting the properties or labels of the edges in a graph, based on the features of the nodes and edges, and the structure of the graph. Edge-level graph learning can be useful for tasks such as link prediction, recommendation systems, fraud detection, and social network analysis.
Link prediction refers to the problem of predicting missing or future edges/links in a graph or network. Given a snapshot of a network, the goal is to estimate the likelihood of an edge forming between two nodes based on the existing graph structure and node attributes.
In an e-commerce graph, link prediction can be used to predict new edges between users and products that represent potential future purchases. Specifically, we can predict which products a user may be interested in purchasing, based on their previous interactions as well as similar users’ purchase patterns.
Figure 2.4 ...
