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

arXiv: https://arxiv.org/abs/2606.08306 · HTML: https://mlsanity.com/paper/2606.08306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [Multilayer Networks](https://mlsanity.com/paper/1309.7233/) (2013)
- [Deep Graph Representation Learning and Optimization for Influence Maximization](https://mlsanity.com/paper/2305.02200/) (2023)
- [Spreading processes in Multilayer Networks](https://mlsanity.com/paper/1405.4329/) (2014)
- [A multilayer network dataset of interaction and influence spreading in a virtual world](https://mlsanity.com/paper/1702.06373/) (2017)
- [Graph Bayesian Optimization for Multiplex Influence Maximization](https://mlsanity.com/paper/2403.18866/) (2024)
- [Rank-Refining Seed Selection Methods for Budget Constrained Influence Maximisation in Multilayer Networks under Linear Threshold Model](https://mlsanity.com/paper/2405.18059/) (2024)
- [Identifying Super Spreaders in Multilayer Networks](https://mlsanity.com/paper/2505.20980/) (2025)

## Abstract (arXiv)

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.