Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms
cs.LG, cs.NI
Submitted: 2026-04-03
Updated: 2026-09-07
Comments: Accepted at Transactions of Machine Learning Research (TMLR) 2026
Code: https://github.com/BNN-UPC/Papers
License: http://creativecommons.org/licenses/by/4.0/
The gist: Routing algorithms are crucial for efficient computer network operations, and in many settings they must be able to react to traffic bursts within milliseconds.
Terminology
Abstract
Routing algorithms are crucial for efficient computer network operations, and in many settings they must be able to react to traffic bursts within milliseconds. Live telemetry data can provide informative signals to routing algorithms, and recent work has trained neural networks to exploit such signals for traffic-aware routing. Yet, aggregating network-wide information is subject to communication delays, and existing neural approaches either assume unrealistic delay-free global states, or restrict routers to purely local telemetry. This leaves their deployability in real-world environments unclear. We cast telemetry-aware routing as a delay-aware closed-loop control problem and introduce a framework that trains and evaluates neural routing algorithms, while explicitly modeling communication and inference delays. On top of this framework, we propose LOGGIA, a scalable graph neural routing algorithm that predicts log-space link weights from attributed topology-and-telemetry graphs. It utilizes a data-driven pre-training stage, followed by on-policy Reinforcement Learning. Across synthetic and real network topologies, and unseen mixed TCP/UDP traffic sequences, LOGGIA consistently outperforms shortest-path baselines, whereas neural baselines fail once realistic delays are enforced. Our experiments further suggest that neural routing algorithms like LOGGIA perform best when deployed fully locally, i.e., observing network states and inferring actions at every router individually, as opposed to centralized decision making.
Sources
- Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
- Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
- Fast Graph Representation Learning with PyTorch Geometric
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- REPETITA: Repeatable Experiments for Performance Evaluation of Traffic-Engineering Algorithms
- Adam: A Method for Stochastic Optimization
- Fast Traffic Engineering by Gradient Descent with Learned Differentiable Routing
- Proximal Policy Optimization Algorithms
- Impact of Evolving Protocols and COVID-19 on Internet Traffic Shares
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks