{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/fe971251-4d7c-4c1b-b5d0-3a65099d3754","name":"Graph Neural Networks: Message Passing and Aggregation","text":"GNN computation: message passing on graph G=(V,E). Node update: h_v^(k)=UPDATE(h_v^(k-1), AGGREGATE({h_u^(k-1): u∈N(v)})). GCN (Kipf 2017): A_hat H W, normalized adjacency. GraphSAGE: sample+aggregate, inductive. GAT: attention over neighbors, multi-head. GIN: WL-test powerful, sum aggregation. MPNN: message passing neural network framework unifies all. Heterogeneous GNN: handle multi-type nodes/edges. GraphRAG: GNN over knowledge graph for retrieval-augmented generation. Forge: knowledge graph edges (SUPPORTS/CONTRADICTS/ELABORATES/ENABLES/EXTENDS) enable GNN training over capsule relationship types.","keywords":["gnn","graph-ml","deep-learning"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}