ARRQP: Anomaly Resilient Real-time QoS Prediction Framework with Graph Convolution

TL;DR

ARRQP is a real-time QoS prediction framework that leverages graph convolution and robust techniques to handle anomalies, data sparsity, and cold-start issues, improving prediction accuracy in service-oriented architectures.

Contribution

The paper introduces ARRQP, a novel graph convolution-based framework that enhances anomaly resilience and addresses cold-start and data sparsity challenges in QoS prediction.

Findings

Achieves higher prediction accuracy on WS-DREAM dataset

Effectively detects and handles grey-sheep and outliers

Addresses cold-start by emphasizing contextual features

Abstract

In the realm of modern service-oriented architecture, ensuring Quality of Service (QoS) is of paramount importance. The ability to predict QoS values in advance empowers users to make informed decisions. However, achieving accurate QoS predictions in the presence of various issues and anomalies, including outliers, data sparsity, grey-sheep instances, and cold-start scenarios, remains a challenge. Current state-of-the-art methods often fall short when addressing these issues simultaneously, resulting in performance degradation. In this paper, we introduce a real-time QoS prediction framework (called ARRQP) with a specific emphasis on improving resilience to anomalies in the data. ARRQP utilizes the power of graph convolution techniques to capture intricate relationships and dependencies among users and services, even when the data is limited or sparse. ARRQP integrates both contextual information and collaborative insights, enabling a comprehensive understanding of user-service interactions. By utilizing robust loss functions, ARRQP effectively reduces the impact of outliers during the model training. Additionally, we introduce a sparsity-resilient grey-sheep detection method, which is subsequently treated separately for QoS prediction. Furthermore, we address the cold-start problem by emphasizing contextual features over collaborative features. Experimental results on the benchmark WS-DREAM dataset demonstrate the framework's effectiveness in achieving accurate and timely QoS predictions.