Temporal Hyperbolic Graph Representation Learning for Scale-Free Internet Routing and Delay Prediction
arXiv:2605.28155v1 Announce Type: new Abstract: Predicting Internet round-trip time (RTT) is critical for routing optimization, quality-of-service (QoS) provisioning, and traffic engineering, yet remains challenging due to long-term temporal dependencies, evolving routing dynamics, and heavy-tailed latency distributions. While Temporal Graph Neural Networks (TGNNs) can model evolving network topologies, most existing approaches operate in Euclidean space, which poorly captures the hierarchical and scale-free structure of Internet routing graphs. Hyperbolic geometry provides a more suitable rep
The increasing complexity and scale of global internet infrastructure, coupled with the limitations of Euclidean geometry in modeling its structure, necessitate more advanced predictive analytics for network optimization.
Improved internet routing and delay prediction directly impacts the performance of vast digital economies, autonomous systems, and real-time AI applications, making global connectivity more efficient and reliable.
This research introduces a novel approach using hyperbolic geometry for graph representation learning, offering more accurate and robust predictions for scale-free internet routing, thereby enhancing network resilience and efficiency.
- · Internet Service Providers
- · Cloud Computing Platforms
- · AI/ML Infrastructure Providers
- · Telecommunications Equipment Manufacturers
- · Legacy Network Optimization Solutions
- · Systems reliant on imprecise network predictions
More stable and faster internet connections for end-users and improved QoS for critical online services.
Enhanced efficiency in data centers and cloud regions, reducing operational costs and enabling more distributed compute architectures.
Accelerated development of real-time AI applications and autonomous decision-making systems that are highly sensitive to network latency and reliability.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG