DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks

2025-11-13

AI Summary

To address the challenges of complex cross-layer KPI interactions and scarce expert annotations in root-cause diagnosis of QoE degradation in mobile networks, this paper proposes an end-to-end diagnostic framework that jointly leverages weakly supervised data and domain expertise. Methodologically, it introduces a class-conditional diffusion model for time-series data augmentation, integrated with denoising contrastive pretraining and expert-label-guided fine-tuning to achieve noise-robust representation learning and semantic alignment under few-shot conditions. The framework unifies data-driven and knowledge-guided diagnostic pathways within a single architecture. Evaluated on real-world operator data, it achieves state-of-the-art performance, significantly outperforming conventional machine learning and semi-supervised time-series classification methods in root-cause identification accuracy. Results demonstrate both effectiveness in complex cross-layer attribution tasks and strong generalization capability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Diffusion Models for Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Diagnosing the root causes of Quality of Experience (QoE) degradations in operational mobile networks is challenging due to complex cross-layer interactions among kernel performance indicators (KPIs) and the scarcity of reliable expert annotations. Although rule-based heuristics can generate labels at scale, they are noisy and coarse-grained, limiting the accuracy of purely data-driven approaches. To address this, we propose DK-Root, a joint data-and-knowledge-driven framework that unifies scalable weak supervision with precise expert guidance for robust root-cause analysis. DK-Root first pretrains an encoder via contrastive representation learning using abundant rule-based labels while explicitly denoising their noise through a supervised contrastive objective. To supply task-faithful data augmentation, we introduce a class-conditional diffusion model that generates KPIs sequences preserving root-cause semantics, and by controlling reverse diffusion steps, it produces weak and strong augmentations that improve intra-class compactness and inter-class separability. Finally, the encoder and the lightweight classifier are jointly fine-tuned with scarce expert-verified labels to sharpen decision boundaries. Extensive experiments on a real-world, operator-grade dataset demonstrate state-of-the-art accuracy, with DK-Root surpassing traditional ML and recent semi-supervised time-series methods. Ablations confirm the necessity of the conditional diffusion augmentation and the pretrain-finetune design, validating both representation quality and classification gains.

Problem

• Diagnosing root causes of QoE degradations in mobile networks
• Addressing noisy rule-based labels and limited expert annotations
• Improving robustness of root-cause analysis through joint data-knowledge framework

Innovation

• Joint data-knowledge framework for root cause analysis
• Contrastive learning with denoising for representation pretraining
• Conditional diffusion model for semantic-preserving data augmentation