# Cascaded Transformer for Robust and Scalable SLA Decomposition via Amortized Optimization

arXiv: https://arxiv.org/abs/2601.11859 · HTML: https://mlsanity.com/paper/2601.11859/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems](https://mlsanity.com/paper/2003.04919/) (2020)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning](https://mlsanity.com/paper/2501.18708/) (2025)
- [Domain-informed graph neural networks: a quantum chemistry case study](https://mlsanity.com/paper/2208.11934/) (2022)
- [SLA Decomposition for Network Slicing: A Deep Neural Network Approach](https://mlsanity.com/paper/2407.15288/) (2024)
- [Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems](https://mlsanity.com/paper/2408.08968/) (2024)
- [RAILS: Risk-Aware Iterated Local Search for Joint SLA Decomposition and Service Provider Management in Multi-Domain Networks](https://mlsanity.com/paper/2502.06674/) (2025)
- [Odin: Effective End-to-End SLA Decomposition for 5G/6G Network Slicing via Online Learning](https://mlsanity.com/paper/2509.13511/) (2025)

## Abstract (arXiv)

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.