Temporal Graph Network
Definition
Temporal graph models process relationships and states together with their temporal changes.
A graph model that processes time-stamped node and edge events as well as changing states.
Simply explained
It’s not only important who is connected to whom, but also when this connection changes. The model tracks this development.
Why it matters in practice
The term helps to select, develop, evaluate AI systems in a well-founded manner and realistically assess their technical risks.
Example from business
A supplier detects unusual changes in time-dependent supply and transaction relationships.
Limits and pitfalls
- Temporal leakage, incorrect event order, and missing new nodes distort evaluation and operation.
Origin & history
Rossi and co-authors published the TGN framework for dynamic graphs in 2020.
Use in mid-sized companies
- Possible application: A supplier detects unusual changes in time-dependent supply and transaction relationships.
Frequently asked questions
What does Temporal Graph Neural Network mean?
A graph model that processes time-stamped node and edge events as well as changing states. What should be watched out for? Temporal leakage, incorrect event order, and missing new nodes distort evaluation and operation.
Sources
- Temporal Graph Networks · Rossi et al., Temporal Graph Networks
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: