Score: 0

Preventing Model Collapse via Contraction-Conditioned Neural Filters

Published: November 30, 2025 | arXiv ID: 2512.00757v1

By: Zongjian Han , Yiran Liang , Ruiwen Wang and more

Potential Business Impact:

Prevents AI from forgetting what it learned.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

This paper presents a neural network filter method based on contraction operators to address model collapse in recursive training of generative models. Unlike \cite{xu2024probabilistic}, which requires superlinear sample growth ($O(t^{1+s})$), our approach completely eliminates the dependence on increasing sample sizes within an unbiased estimation framework by designing a neural filter that learns to satisfy contraction conditions. We develop specialized neural network architectures and loss functions that enable the filter to actively learn contraction conditions satisfying Assumption 2.3 in exponential family distributions, thereby ensuring practical application of our theoretical results. Theoretical analysis demonstrates that when the learned contraction conditions are satisfied, estimation errors converge probabilistically even with constant sample sizes, i.e., $\limsup_{t\to\infty}\mathbb{P}(\|\mathbf{e}_t\|>δ)=0$ for any $δ>0$. Experimental results show that our neural network filter effectively learns contraction conditions and prevents model collapse under fixed sample size settings, providing an end-to-end solution for practical applications.

Country of Origin
🇨🇳 China

Page Count
14 pages

Category
Computer Science:
Machine Learning (CS)