QoSBERT: An Uncertainty-Aware Approach based on Pre-trained Language Models for Service Quality Prediction

2025-05-09

AI Summary

This paper addresses the lack of trustworthy uncertainty quantification in cloud service QoS prediction. We propose the first QoS semantic regression framework, which models response time and throughput prediction as semantic regression tasks over service natural-language metadata. The framework integrates BERT-style pre-trained language models, attention-based pooling, and a lightweight MLP regressor, augmented with Monte Carlo Dropout for well-calibrated uncertainty estimation. We further introduce an uncertainty-guided sample selection mechanism to enhance robustness under low-resource conditions. Evaluated on standard QoS benchmarks, our method reduces MAE and RMSE for response time prediction by 11.7% and 6.7%, respectively, and decreases throughput MAE by 6.9%. Crucially, it produces highly confidence-calibrated prediction intervals, significantly improving risk-aware service selection and decision-making reliability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accurate prediction of Quality of Service (QoS) metrics is fundamental for selecting and managing cloud based services. Traditional QoS models rely on manual feature engineering and yield only point estimates, offering no insight into the confidence of their predictions. In this paper, we propose QoSBERT, the first framework that reformulates QoS prediction as a semantic regression task based on pre trained language models. Unlike previous approaches relying on sparse numerical features, QoSBERT automatically encodes user service metadata into natural language descriptions, enabling deep semantic understanding. Furthermore, we integrate a Monte Carlo Dropout based uncertainty estimation module, allowing for trustworthy and risk-aware service quality prediction, which is crucial yet underexplored in existing QoS models. QoSBERT applies attentive pooling over contextualized embeddings and a lightweight multilayer perceptron regressor, fine tuned jointly to minimize absolute error. We further exploit the resulting uncertainty estimates to select high quality training samples, improving robustness in low resource settings. On standard QoS benchmark datasets, QoSBERT achieves an average reduction of 11.7% in MAE and 6.7% in RMSE for response time prediction, and 6.9% in MAE for throughput prediction compared to the strongest baselines, while providing well calibrated confidence intervals for robust and trustworthy service quality estimation. Our approach not only advances the accuracy of service quality prediction but also delivers reliable uncertainty quantification, paving the way for more trustworthy, data driven service selection and optimization.

Problem

• Predicting QoS metrics accurately for cloud services
• Overcoming manual feature engineering in traditional QoS models
• Providing uncertainty-aware QoS predictions for trustworthy service selection

Innovation

• Uses pre-trained language models for semantic regression
• Integrates Monte Carlo Dropout for uncertainty estimation
• Applies attentive pooling and lightweight MLP regressor