Towards Graph Foundation Models for Dynamics in Complex Networked Systems: Lessons from Super-Spreader Identification in Multilayer Networks

• URL: http://arxiv.org/abs/2606.08306v1
• Date: Sat, 06 Jun 2026 19:30:43 GMT
• Title: Towards Graph Foundation Models for Dynamics in Complex Networked Systems: Lessons from Super-Spreader Identification in Multilayer Networks
• Abstract summary: We argue that inductive cross-network generalisation is a necessary prerequisite for Graph Foundation Models (GFMs)<n>We outline five open challenges towards building GFMs for network dynamics: scale, many-layer generalisation, self-supervised pretraining, cross-task transfer, and node-attribute integration.
• Score: 0.48933451909251774
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Network dynamics - including spreading, influence maximisation, and epidemic modelling - remain largely confined to the transductive paradigm, where models are trained on a single network and cannot be reused on unseen graphs without retraining. We argue that inductive cross-network generalisation is a necessary prerequisite for Graph Foundation Models (GFMs) in this domain and propose four design properties towards this goal. As a proof of concept, ts-net (TopSpreadersNetwork), trained solely on synthetic multilayer networks (MLNs), demonstrates zero-shot generalisation to real-world MLNs of varying size and layer count, outperforming classical heuristics and transductive baselines on three of four metrics. Based on ts-net's performance, we further outline five open challenges towards building GFMs for network dynamics: scale, many-layer generalisation, self-supervised pretraining, cross-task transfer, and node-attribute integration.

Related papers

• Differentiable Lifting for Topological Neural Networks [49.208571794040374]
  Topological neural networks (TNNs) enable leveraging high-order structures on graphs.<n>DiffLift is a framework for learning graph liftings to hypergraphs and cellular- and simplicial complexes.<n>Our approach leads to gains of up to 45% over static liftings, including both connectivity- and feature-based ones.
  arXiv  Detail & Related papers  (2026-08-02T11:30:09Z)
• Learning Ad Hoc Network Dynamics via Graph-Structured World Models [0.0]
  We propose a graph structured recurrent state space model that maintains per node latent states with cross node multi head attention to learn the dynamics jointly from offline trajectories.<n>Across 27 evaluation scenarios spanning MANET, VANET, FANET, WSN and tactical networks with N=30 to 1000 nodes, the learned policy maintains high connectivity with only trained for N=50.
  arXiv  Detail & Related papers  (2026-04-16T09:32:15Z)
• Ordered Topological Deep Learning: a Network Modeling Case Study [7.358417570496687]
  We revisit RouteNet's sophisticated design and uncover its hidden connection to Topological Deep Learning (TDL)<n>This paper presents OrdGCCN, a novel TDL framework that introduces the notion of ordered neighbors in arbitrary discrete topological spaces.<n>To the best of our knowledge, this marks the first successful real-world application of state-of-the-art TDL principles.
  arXiv  Detail & Related papers  (2025-03-20T23:15:12Z)
• Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement [62.91536661584656]
  We propose a dual-module framework, Cell-embedded and Feature-enhanced Graph Neural Network (aka, CeFeGNN) for learning.<n>We embed learnable cell attributions to the common node-edge message passing process, which better captures the spatial dependency of regional features.<n>Experiments on various PDE systems and one real-world dataset demonstrate that CeFeGNN achieves superior performance compared with other baselines.
  arXiv  Detail & Related papers  (2024-09-26T16:22:08Z)
• Towards a graph-based foundation model for network traffic analysis [3.0558245652654907]
  Foundation models can grasp the complexities of network traffic dynamics and adapt to any specific task or environment with minimal fine-tuning. Previous approaches have used tokenized hex-level packet data. We propose a new, efficient graph-based alternative at the flow-level.
  arXiv  Detail & Related papers  (2024-09-12T15:04:34Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Generalization and Estimation Error Bounds for Model-based Neural Networks [78.88759757988761]
  We show that the generalization abilities of model-based networks for sparse recovery outperform those of regular ReLU networks. We derive practical design rules that allow to construct model-based networks with guaranteed high generalization.
  arXiv  Detail & Related papers  (2023-04-19T16:39:44Z)
• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks [27.600081147252155]
  We develop a novel graph sumable framework to maximize energy efficiency in wireless communication networks. We show the permutation training which is a desirable property for models of wireless network data. Results demonstrate its generalizability across different network topologies.
  arXiv  Detail & Related papers  (2022-01-27T20:23:24Z)
• Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [79.28094304325116]
  Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points. We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
  arXiv  Detail & Related papers  (2020-11-14T11:09:51Z)
• 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)
• Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework [6.790281989130923]
  InfoMotif is a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in graph neural networks (GNNs) We show significant gains (3-10% accuracy) across six diverse, real-world datasets.
  arXiv  Detail & Related papers  (2020-09-11T02:03:09Z)
• Pre-Trained Models for Heterogeneous Information Networks [57.78194356302626]
  We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network. PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.
  arXiv  Detail & Related papers  (2020-07-07T03:36:28Z)

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.