Vertical Federated Learning for Failure-Cause Identification in Disaggregated Microwave Networks

2025-02-05

AI Summary

In multi-vendor decoupled microwave networks, conflicting commercial interests prevent sharing of sensitive fault data, rendering conventional centralized machine learning infeasible. To address this, we propose a vertical federated learning (VFL) framework that—uniquely for real-world microwave hardware fault diagnosis—integrates SplitNNs and FedTree, two complementary VFL paradigms. Our framework enables cross-operator distributed root-cause identification while strictly preserving data locality: no raw data or model parameters leave their respective operator domains. Experiments across multi-vendor deployments demonstrate that our approach achieves an F1-score within ≤1% of the centralized baseline, while substantially mitigating leakage risks of sensitive information at both gradient and model-parameter levels. This work establishes a practical, privacy-preserving VFL paradigm for intelligent operations and maintenance in privacy-sensitive communication infrastructure.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Adversarial Attacks & Robustness
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Machine Learning (ML) has proven to be a promising solution to provide novel scalable and efficient fault management solutions in modern 5G-and-beyond communication networks. In the context of microwave networks, ML-based solutions have received significant attention. However, current solutions can only be applied to monolithic scenarios in which a single entity (e.g., an operator) manages the entire network. As current network architectures move towards disaggregated communication platforms in which multiple operators and vendors collaborate to achieve cost-efficient and reliable network management, new ML-based approaches for fault management must tackle the challenges of sharing business-critical information due to potential conflicts of interest. In this study, we explore the application of Federated Learning in disaggregated microwave networks for failure-cause identification using a real microwave hardware failure dataset. In particular, we investigate the application of two Vertical Federated Learning (VFL), namely using Split Neural Networks (SplitNNs) and Federated Learning based on Gradient Boosting Decision Trees (FedTree), on different multi-vendor deployment scenarios, and we compare them to a centralized scenario where data is managed by a single entity. Our experimental results show that VFL-based scenarios can achieve F1-Scores consistently within at most a 1% gap with respect to a centralized scenario, regardless of the deployment strategies or model types, while also ensuring minimal leakage of sensitive-data.

Problem

• Identify failure causes in disaggregated microwave networks
• Apply Vertical Federated Learning for multi-vendor collaboration
• Ensure minimal sensitive-data leakage in fault management

Innovation

• Vertical Federated Learning
• Split Neural Networks
• Gradient Boosting Decision Trees