GATNextHop: A GAT for Shortest Path Routing with Cross-Topology Generalization

• URL: http://arxiv.org/abs/2608.23917v1
• Date: Mon, 24 Aug 2026 23:50:52 GMT
• Title: GATNextHop: A GAT for Shortest Path Routing with Cross-Topology Generalization
• Abstract summary: This paper proposes the GATNextHop model to determine whether a Graph Neural Network, namely the Graph Attention Network, can approximate shortest paths and generalize across topologies.<n>Performance will be evaluated in terms of accuracy, inference speed, and generalization, comparing the GNN against Dijkstra's algorithm to quantify trade-offs between learned and classical routing approaches.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topology, limiting scalability in dynamic or large-scale networks. This paper proposes the GATNextHop model to determine whether a Graph Neural Network, namely the Graph Attention Network, can approximate shortest paths and generalize across topologies. By training on synthetic graphs and evaluating on real-world Internet Service Provider networks from the Internet Topology Zoo, we aim to benchmark our model's ability to learn routing heuristics that transfer across network structures. Performance will be evaluated in terms of accuracy, inference speed, and generalization, comparing the GNN against Dijkstra's algorithm to quantify trade-offs between learned and classical routing approaches.

Related papers

• Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs [81.39865232674413]
  Graph Neural Networks (GNNs) have emerged as a powerful tool for wireless resource allocation.<n>This work establishes theoretical results for transferability of GNNs over graphs derived from sparse Random Geometric Graphs (RGGs)
  arXiv  Detail & Related papers  (2026-06-02T15:42:14Z)
• Knowledge-Guided Machine Learning for Stabilizing Near-Shortest Path Routing [3.595536209220219]
  We propose a simple algorithm that needs only a few data samples from a single graph for learning local routing policies.<n>We learn a new policy, which we call GreedyTensile routing, that almost always outperforms greedy forwarding.<n>We demonstrate the explainability and ultra-low latency run-time operation of Greedy Tensile routing.
  arXiv  Detail & Related papers  (2025-09-08T12:56:42Z)
• Graph neural networks extrapolate out-of-distribution for shortest paths [13.300757448796361]
  Graph Neural Networks (GNNs) are trained to minimize a sparsity-regularized loss over a small set of shortest path instances.<n>We show that GNNs trained by gradient descent are able to minimize this loss and extrapolate in practice.
  arXiv  Detail & Related papers  (2025-03-24T21:52:05Z)
• Opportunistic Routing in Wireless Communications via Learnable State-Augmented Policies [7.512221808783587]
  This paper addresses the challenge of packet-based information routing in large-scale wireless communication networks.<n>Opportunistic routing exploits the broadcast nature of wireless communication to dynamically select optimal forwarding nodes.<n>We propose a State-Augmentation (SA) based distributed optimization approach aimed at maximizing the total information handled by the source nodes in the network.
  arXiv  Detail & Related papers  (2025-03-05T18:44:56Z)
• Network Tomography with Path-Centric Graph Neural Network [8.789611631435024]
  We argue that a good network tomography requires synergizing the knowledge from both data and appropriate inductive bias from (partial) prior knowledge.<n>We propose Deep Network Tomography (DeepNT), a novel framework that leverages a path-centric graph neural network to predict path performance metrics.
  arXiv  Detail & Related papers  (2025-02-23T04:08:46Z)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• Learning State-Augmented Policies for Information Routing in Communication Networks [84.76186111434818]
  We develop a novel State Augmentation (SA) strategy to maximize the aggregate information at source nodes using graph neural network (GNN) architectures.<n>We leverage an unsupervised learning procedure to convert the output of the GNN architecture to optimal information routing strategies.<n>In the experiments, we perform the evaluation on real-time network topologies to validate our algorithms.
  arXiv  Detail & Related papers  (2023-09-30T04:34:25Z)
• Packet Routing with Graph Attention Multi-agent Reinforcement Learning [4.78921052969006]
  We develop a model-free and data-driven routing strategy by leveraging reinforcement learning (RL) Considering the graph nature of the network topology, we design a multi-agent RL framework in combination with Graph Neural Network (GNN)
  arXiv  Detail & Related papers  (2021-07-28T06:20:34Z)
• Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition [97.14064057840089]
  We propose a method to automatically find a compact and problem-specific network for graph convolutional networks in a progressive manner. Experimental results on two datasets for skeleton-based human action recognition indicate that the proposed method has competitive or even better classification performance.
  arXiv  Detail & Related papers  (2020-11-11T09:57:49Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.