Graph Neural Modeling of Network Flows (2209.05208v3)
Abstract: Network flow problems, which involve distributing traffic such that the underlying infrastructure is used effectively, are ubiquitous in transportation and logistics. Among them, the general Multi-Commodity Network Flow (MCNF) problem concerns the distribution of multiple flows of different sizes between several sources and sinks, while achieving effective utilization of the links. Due to the appeal of data-driven optimization, these problems have increasingly been approached using graph learning methods. In this paper, we propose a novel graph learning architecture for network flow problems called Per-Edge Weights (PEW). This method builds on a Graph Attention Network and uses distinctly parametrized message functions along each link. We extensively evaluate the proposed solution through an Internet flow routing case study using $17$ Service Provider topologies and $2$ routing schemes. We show that PEW yields substantial gains over architectures whose global message function constrains the routing unnecessarily. We also find that an MLP is competitive with other standard architectures. Furthermore, we analyze the relationship between graph structure and predictive performance for data-driven routing of flows, an aspect that has not been considered by existing work in the area.
- Ravindra K. Ahuja. Network Flows: Theory, Algorithms, and Applications. Prentice Hall, Englewood Cliffs, NJ, 1993.
- Towards real-time routing optimization with deep reinforcement learning: Open challenges. In HPSR, 2021.
- Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261, 2018.
- Ulrik Brandes. A faster algorithm for betweenness centrality. Journal of Mathematical Sociology, 25(2):163–177, 2001.
- Relational graph attention networks. arXiv preprint arXiv:1904.05811, 2019.
- Combinatorial optimization and reasoning with graph neural networks. In IJCAI, 2021.
- Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In AAAI, 2020.
- Maximum flow and minimum-cost flow in almost-linear time. In FOCS, 2022.
- Introduction to Algorithms. MIT Press, Fourth edition, 2022.
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In NeurIPS, 2016.
- R-GCN: The R could stand for random. arXiv preprint arXiv:2203.02424, 2022.
- A fair comparison of graph neural networks for graph classification. In ICLR, 2020.
- Why (and how) networks should run themselves. arXiv preprint arXiv:1710.11583, 2017.
- Deriving traffic demands for operational IP networks: Methodology and experience. IEEE/ACM Transactions On Networking, 9(3):265–279, 2001.
- Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019.
- Internet Traffic Engineering by Optimizing OSPF Weights. In IEEE INFOCOM, 2000.
- Optimizing OSPF/IS-IS Weights in a Changing World. IEEE Journal on Selected Areas in Communications, 20(4):756–767, 2002.
- Increasing internet capacity using local search. Computational Optimization and Applications, 29(1):13–48, 2004.
- Repetita: Repeatable experiments for performance evaluation of traffic-engineering algorithms. arXiv preprint arXiv:1710.08665, 2017.
- Neural bipartite matching. In ICML Workshop on Graph Representation Learning and Beyond (GRL+), 2020.
- Learning and Generating Distributed Routing Protocols Using Graph-Based Deep Learning. In Big-DAMA, 2018.
- Neural Message Passing for Quantum Chemistry. In ICML, 2017.
- Definitive MPLS Network Designs. Cisco Press, 2005.
- On low-latency-capable topologies, and their impact on the design of intra-domain routing. In SIGCOMM’18, 2018.
- Recent Advances in Networking. 2013.
- Exploring network structure, dynamics, and function using networkx. In SciPy, 2008.
- Inductive Representation Learning on Large Graphs. In NeurIPS, 2017.
- A declarative and expressive approach to control forwarding paths in carrier-grade networks. ACM SIGCOMM Computer Communication Review, 45(4):15–28, 2015.
- GDDR: GNN-based Data-Driven Routing. In ICDCS, 2021.
- C. Hopps. Analysis of an equal-cost multi-path algorithm. RFC 2992, RFC Editor, November 2000.
- T. Chiang Hu. Multi-commodity network flows. Operations Research, 11(3):344–360, 1963.
- J. D. Hunter. Matplotlib: A 2D graphics environment. Computing in Science & Engineering, 9(3):90–95, 2007.
- Unleashing the potential of data-driven networking. In COMSNETS, 2017.
- Walking the tightrope: Responsive yet stable traffic engineering. In SIGCOMM, 2005.
- Adam: A Method for Stochastic Optimization. In ICLR, 2015.
- Semi-Supervised Classification with Graph Convolutional Networks. In ICLR, 2017.
- The Internet Topology Zoo. IEEE Journal on Selected Areas in Communications, 29(9):1765–1775, 2011.
- Gated Graph Sequence Neural Networks. In ICLR, 2017.
- Wes McKinney. pandas: a foundational Python library for data analysis and statistics. Python for High Performance and Scientific Computing, 14(9):1–9, 2011.
- PyTorch: An imperative style, high-performance deep learning library. In NeurIPS, 2019.
- Harald Räcke. Optimal hierarchical decompositions for congestion minimization in networks. In STOC, 2008.
- Deep neural networks for network routing. In IJCNN, 2019.
- Matthew Roughan. Simplifying the synthesis of internet traffic matrices. ACM SIGCOMM Computer Communication Review, 35(5):93–96, 2005.
- Unveiling the potential of graph neural networks for network modeling and optimization in SDN. In SOSR, 2019.
- The Graph Neural Network Model. IEEE Transactions on Neural Networks, 20(1):61–80, 2009.
- Modeling relational data with graph convolutional networks. In ESWC, pp. 593–607. Springer, 2018.
- Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks, 8(3):714–735, 1997.
- Éva Tardos. A strongly polynomial algorithm to solve combinatorial linear programs. Operations Research, 34(2):250–256, 1986.
- Learning to route. In ACM HotNets, 2017.
- Graph attention networks. In ICLR, 2018.
- Michael L. Waskom. Seaborn: statistical data visualization. Journal of Open Source Software, 6(60):3021, 2021.
- What can neural networks reason about? In ICLR, 2020.
- Experience-driven networking: A deep reinforcement learning based approach. In IEEE INFOCOM, 2018.
- CFR-RL: Traffic engineering with reinforcement learning in SDN. IEEE Journal on Selected Areas in Communications, 38(10):2249–2259, 2020.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.