Cascaded Transformer for Robust and Scalable SLA Decomposition via Amortized Optimization

2026-01-17

AI Summary

This work addresses the limitations of existing end-to-end SLA decomposition methods, which rely on computationally intensive iterative optimization and thus struggle to meet the stringent real-time and scalability demands of 6G network slicing. To overcome this challenge, the authors propose Casformer—a cascaded Transformer architecture that uniquely integrates amortized optimization with domain-aware neural networks. By leveraging an intra-domain historical feedback encoder and an inter-domain dependency aggregator, Casformer enables feedforward, non-iterative SLA decomposition for the first time. Extensive evaluations demonstrate that the proposed method significantly outperforms state-of-the-art approaches across diverse network conditions, achieving superior decomposition quality, robustness, and scalability while maintaining low runtime complexity—making it well-suited for real-time SLA management in 5G and beyond.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The evolution toward 6G networks increasingly relies on network slicing to provide tailored, End-to-End (E2E) logical networks over shared physical infrastructures. A critical challenge is effectively decomposing E2E Service Level Agreements (SLAs) into domain-specific SLAs, which current solutions handle through computationally intensive, iterative optimization processes that incur substantial latency and complexity. To address this, we introduce Casformer, a cascaded Transformer architecture designed for fast, optimization-free SLA decomposition. Casformer leverages historical domain feedback encoded through domain-specific Transformer encoders in its first layer, and integrates cross-domain dependencies using a Transformer-based aggregator in its second layer. The model is trained under a learning paradigm inspired by Domain-Informed Neural Networks (DINNs), incorporating risk-informed modeling and amortized optimization to learn a stable, forward-only SLA decomposition policy. Extensive evaluations demonstrate that Casformer achieves improved SLA decomposition quality against state-of-the-art optimization-based frameworks, while exhibiting enhanced scalability and robustness under volatile and noisy network conditions. In addition, its forward-only design reduces runtime complexity and simplifies deployment and maintenance. These insights reveal the potential of combining amortized optimization with Transformer-based sequence modeling to advance network automation, providing a scalable and efficient solution suitable for real-time SLA management in advanced 5G-and-beyond network environments.

Problem

• SLA decomposition
• network slicing
• 6G networks
• End-to-End SLA
• domain-specific SLA

Innovation

• Cascaded Transformer
• Amortized Optimization
• SLA Decomposition
• Domain-Informed Neural Networks
• Network Slicing