# Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study

arXiv: https://arxiv.org/abs/2609.18704 · HTML: https://mlsanity.com/paper/2609.18704/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Hierarchical Graph Pooling with Structure Learning](https://mlsanity.com/paper/1911.05954/) (2019)
- [DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks](https://mlsanity.com/paper/2104.06700/) (2021)
- [Covariant Compositional Networks For Learning Graphs](https://mlsanity.com/paper/1801.02144/) (2018)
- [RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDN](https://mlsanity.com/paper/1910.01508/) (2019)
- [6G Digital Twin Networks: From Theory to Practice](https://mlsanity.com/paper/2212.02032/) (2022)
- [Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities](https://mlsanity.com/paper/2112.14792/) (2021)
- [Machine Learning for Networking: Workflow, Advances and Opportunities](https://mlsanity.com/paper/1709.08339/) (2017)
- [Network Digital Twin: Context, Enabling Technologies and Opportunities](https://mlsanity.com/paper/2205.14206/) (2022)
- [Digital Twin for Networking: A Data-driven Performance Modeling Perspective](https://mlsanity.com/paper/2206.00310/) (2022)
- [Network Digital Twin for 6G and Beyond: An End-to-End View Across Multi-Domain Network Ecosystems](https://mlsanity.com/paper/2506.01609/) (2025)
- [Learnable Digital Twin for Efficient Wireless Network Evaluation](https://mlsanity.com/paper/2306.06574/) (2023)
- [CAVIAR: Co-simulation of 6G Communications, 3D Scenarios and AI for Digital Twins](https://mlsanity.com/paper/2401.03310/) (2024)
- [RouteNet-Gauss: Hardware-Enhanced Network Modeling with Machine Learning](https://mlsanity.com/paper/2501.08848/) (2025)
- [OpenRASE: Service Function Chain Emulation](https://mlsanity.com/paper/2507.22131/) (2025)
- [The Challenges of Trace-Driven Wi-Fi Emulation](https://mlsanity.com/paper/2002.03905/) (2020)
- [RMQFMU: Bridging the Real World with Co-simulation Technical Report](https://mlsanity.com/paper/2107.01010/) (2021)
- [Open World Learning Graph Convolution for Latency Estimation in Routing Networks](https://mlsanity.com/paper/2207.14643/) (2022)
- [Coupling OMNeT++ and mosaik for integrated Co-Simulation of ICT-reliant Smart Grids](https://mlsanity.com/paper/2209.12550/) (2022)
- [Towards a Robust Transport Network With Self-adaptive Network Digital Twin](https://mlsanity.com/paper/2507.20971/) (2025)

## Abstract (arXiv)

Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely on entire topology representations, which are inherently monolithic and lack reusability under topological or traffic changes in the network. This paper introduces a composable NDT approach that decomposes networks into subgraphs represented by reusable unit twins that capture subgraph structure, configuration and traffic behaviours. A lightweight composer aggregates unit twin combinations to create NDTs that predict per-route end-to-end latency through an overall topology. Evaluation across controlled synthetic topologies and diverse traffic scenarios, real-world Topology Zoo topologies, and a public NDT challenge dataset demonstrates that the composable NDTs achieve high in-distribution accuracy while remaining stable under out-of-distribution scenarios. Comparison with monolithic full topology NDTs demonstrates that our composable approach achieves reusability, while achieving comparable or superior accuracy.