KAN-AFT: An Interpretable Nonlinear Survival Model Integrating Kolmogorov-Arnold Networks with Accelerated Failure Time Analysis
Published:Dec 23, 2025 12:16
•1 min read
•ArXiv
Analysis
This article introduces a novel survival model, KAN-AFT, which combines Kolmogorov-Arnold Networks (KANs) with Accelerated Failure Time (AFT) analysis. The focus is on interpretability and nonlinear modeling in survival analysis. The use of KANs suggests an attempt to improve model expressiveness while maintaining some degree of interpretability. The integration with AFT suggests the model aims to predict the time until an event occurs, potentially in medical or engineering contexts. The source being ArXiv indicates this is a pre-print or research paper.
Key Takeaways
- •KAN-AFT is a new survival model.
- •It integrates Kolmogorov-Arnold Networks (KANs) with Accelerated Failure Time (AFT) analysis.
- •The model emphasizes interpretability and nonlinear modeling.
- •The source is ArXiv, indicating a research paper.
Reference
“”