Definition
PinSAGE (Pinterest SAGE) is a Graph Convolutional Network model for large-scale recommendation systems.
Architecture
PinSAGE is based on the GraphSAGE architecture.
Importance-Based Neighbors
We simulate random walks starting from node and count the visits for each node in the random walk. The neighborhood of , , is then defined as the top- nodes with the highest visit counts with respect to node .
Importance Pooling
PinSAGE assigns different weights (normalized visit counts) to different neighbors when aggregating information from a node’s neighborhood. This allows the model to focus on more relevant or influential neighbors.
Curriculum Training
PinSAGE implements a curriculum training strategy, starting with easier examples and gradually moving to more difficult ones. The difficulty of negative samples is based on the visit counts