发表机构
The Ohio State University（俄亥俄州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出有向加权图理论框架，分析网络化自消费生成模型中多模型相互消费合成数据的长期行为，建立收敛条件并刻画固定点，揭示真实数据访问、跨模型消费及图结构对系统稳定性与多样性的影响。
AI 中文摘要
生成式人工智能的广泛部署使得区分合成内容与真实数据变得越来越困难。因此，合成数据不可避免地会被纳入未来几代模型的训练流程中，形成一种自消费训练循环。已有研究探讨了这种递归式自消费训练的影响，但分析大多局限于孤立模型（即模型仅消费自身生成的合成数据）或两个模型之间的简化交互。本文迈出了理解网络化自消费生成模型的第一步，在这种模型中，多个模型通过复杂的交互路径相互消费彼此生成的合成数据。我们引入了一个理论框架，将模型表示为有向加权图中的节点，边的权重控制着模型之间合成数据的流动。利用该框架，我们分析了网络化模型在再训练动态下的长期行为，建立了收敛条件并刻画了由此产生的固定点。我们进一步研究了系统的长期稳定性与多样性如何受到每个模型对真实数据的访问、跨模型数据消费以及交互图结构的影响。
英文摘要
The widespread deployment of generative AI has made it increasingly difficult to distinguish synthetic content from real data. Consequently, synthetic data is inevitably incorporated into the training pipelines of future model generations, forming a self-consuming training loop. Prior work has studied the effects of such recursive self-consuming training, but analyses have largely been limited to isolated models, where a model consumes only its own synthetic data, or to simplified interactions between two models. This paper takes a first step toward understanding networked self-consuming generative models, in which multiple models consume synthetic data generated by one another through complex interaction pathways. We introduce a theoretical framework representing models as nodes in a directed, weighted graph, with edge weights governing the flow of synthetic data among models. Using this framework, we analyze the long-term behavior of networked models under retraining dynamics, establishing conditions for convergence and characterizing the resulting fixed points. We further investigate how the system's long-term stability and diversity are shaped by each model's access to real data, cross-model data consumption, and the structure of the interaction graph.
CommentsPublished as a conference paper at NeurIPS 2026
