# Physically Constrained Federated Additive Models for O-RAN SLA-Risk Prediction

arXiv: https://arxiv.org/abs/2607.21665 · HTML: https://mlsanity.com/paper/2607.21665/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Certified Monotonic Neural Networks](https://mlsanity.com/paper/2011.10219/) (2020)
- [ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms](https://mlsanity.com/paper/2112.09559/) (2021)
- [Constrained Monotonic Neural Networks](https://mlsanity.com/paper/2205.11775/) (2022)
- [Federated Deep Reinforcement Learning for Resource Allocation in O-RAN Slicing](https://mlsanity.com/paper/2208.01736/) (2022)
- [EXPLORA: AI/ML EXPLainability for the Open RAN](https://mlsanity.com/paper/2310.13667/) (2023)
- [Explainable AI in 6G O-RAN: A Tutorial and Survey on Architecture, Use Cases, Challenges, and Future Research](https://mlsanity.com/paper/2307.00319/) (2023)
- [Explanation-Guided Deep Reinforcement Learning for Trustworthy 6G RAN Slicing](https://mlsanity.com/paper/2303.15000/) (2023)
- [DRL-based Latency-Aware Network Slicing in O-RAN with Time-Varying SLAs](https://mlsanity.com/paper/2401.05042/) (2024)
- [From Network Sharing to Multi-tenancy: The 5G Network Slice Broker](https://mlsanity.com/paper/1605.01201/) (2016)
- [Federated Meta-Learning for Traffic Steering in O-RAN](https://mlsanity.com/paper/2209.05874/) (2022)

## Abstract (arXiv)

Proactive service assurance in O-RAN requires predicting per-slice SLA violations before they occur. The prediction model must be auditable by operators and must train across base stations without pooling per-slice KPIs, which are commercially sensitive because slices are leased to individual tenants. Neural additive models (NAMs) offer auditability because each KPI contributes through a visible shape function. However, visibility alone does not guarantee physical validity. On the ColO-RAN testbed dataset, unconstrained NAMs learn effects that contradict wireless physics, for example predicting higher risk when channel quality improves. This failure appears under both local and centralized training, and non-IID federated averaging worsens it. We present Monotone FedNAM, a federated additive model in which KPIs with unambiguous physical direction are represented as monotone splines whose constraints survive FedAvg aggregation by construction, while contestable KPIs remain unconstrained. The model trains and operates as a Non-RT RIC rApp and is compact enough for deployment as a Near-RT RIC xApp. Monotone FedNAM eliminates all monotonicity violations, raises constrained shape consistency from 0.71 to 1.00, generalizes to an unseen scheduling policy, and reduces uplink traffic by 65%, at a cost of 0.04 to 0.07 AUC. These results show that physically constrained federated additive models can support auditable SLA risk inference for multi-tenant O-RAN service assurance