提出可跨网络通用的图模型框架，实现零样本预测超级传播者。
Towards Graph Foundation Models for Dynamics in Complex Networked Systems: Lessons from Super-Spreader Identification in Multilayer Networks
- 设计四类属性支持跨网络泛化，突破传统模型仅限单图训练局限。
- 在真实多层网络上零样本表现优于经典方法与下游模型，四项指标中三项领先。
- 适合关注大规模动态网络建模与通用图模型研究的研究者参考。
网络动态（如传播、影响力最大化、流行病建模）长期受限于归纳范式，即模型仅在单一网络上训练，无法在未见图上直接复用。我们主张，归纳式跨网络泛化是构建图基础模型（GFMs）的必要前提，并提出四项设计原则。作为概念验证，ts-net（TopSpreadersNetwork）仅在合成多层网络（MLNs）上训练，即可在不同规模与层数的真实多层网络上实现零样本泛化，在四项指标中有三项超越经典启发式方法和归纳基线。基于ts-net的表现，我们进一步总结了五个开放挑战：模型规模、多层泛化、自监督预训练、跨任务迁移以及节点属性融合。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。