arXiv：cs.LG· Xiukun Wei, Yang Zhang, Xueru Zhang·· 4 小时前AI 评分40
网络化自消耗生成生态系统的稳定性与多样性
Stability and Diversity of Networked Self-Consuming Generative Ecosystems
AI 导读
该论文首次提出网络化自消耗生成模型的理论框架，将多个模型建模为有向加权图中的节点，边权控制模型间合成数据的流动。研究在重训练动态下分析了模型的长期行为，建立了收敛条件并刻画了固定点，同时揭示了各模型对真实数据的访问、跨模型数据消耗以及交互图结构如何影响系统的长期稳定性与多样性。该成果发表于 NeurIPS 2026。
正文
Abstract: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.
| Comments: | Published as a conference paper at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.09409 [cs.LG] |
| (or arXiv:2610.09409v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09409 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiukun Wei [view email]
[v1]
Wed, 7 Oct 2026 04:11:21 UTC (21,451 KB)
来源：arXiv：cs.LG · arxiv.org