# Graph Representation Learning **Entity class:** Node, Edge, Relationship, And Topology Layer concept **Graph Representation Learning** is a representation in which entities or states are nodes and typed relationships or transitions are edges. Graph Representation Learning matters because the analytic object is a changing, partially observed system rather than a finished dossier. ## Counterterrorism predictive-graph role The page records capability and analytic function. Any claim of a named operational deployment remains subject to the [[wiki/Counterterrorism Predictive Graph Evidence Ladder|evidence ladder]]. The analytic state should distinguish ground truth, observed evidence, inferred state, and predicted state. ## Relationships - **domain router:** [[wiki/Graph Theory|Graph Theory]]. - **ontology neighbors:** [[wiki/Edge Embedding|Edge Embedding]] and [[wiki/Link Prediction|Link Prediction]]. - **synthesis:** [[wiki/Counterterrorism Predictive Graph|Counterterrorism Predictive Graph]] and [[wiki/Predictive Intelligence Loop|Predictive Intelligence Loop]]. ## Sources - [IARPA — AGILE technical overview (accessed September 23, 2026)](https://www.iarpa.gov/images/research-programs/AGILE/AGILE_ModSim_-_Final.pdf) - [IARPA — Making Data Analysis More AGILE (accessed September 23, 2026)](https://www.iarpa.gov/newsroom/article/making-data-analysis-more-agile) **As of:** 2026-09-23