Contrastive Learning-Based Dependency Modeling for Anomaly Detection in Cloud Services

2025-10-15

AI Summary

Detecting anomalies in cloud services is challenging due to complex service dependencies and diverse anomaly patterns. To address this, we propose a dependency modeling and anomaly detection framework integrating contrastive learning. First, we construct a service dependency graph and jointly model temporal dynamics and topological structure for context-aware representation learning. Second, we incorporate contrastive learning to enhance discriminability between normal and anomalous samples, and introduce a temporal consistency constraint to improve representation robustness. Finally, we employ graph convolution to aggregate neighborhood information and jointly optimize the contrastive loss and temporal consistency loss. Evaluated on public benchmarks, our method significantly outperforms state-of-the-art approaches, achieving substantial gains in F1-score and AUC. Moreover, it demonstrates strong robustness under sparse labeling, monitoring noise, and traffic fluctuations.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Graph-based Machine Learning
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper addresses the challenges of complex dependencies and diverse anomaly patterns in cloud service environments by proposing a dependency modeling and anomaly detection method that integrates contrastive learning. The method abstracts service interactions into a dependency graph, extracts temporal and structural features through embedding functions, and employs a graph convolution mechanism to aggregate neighborhood information for context-aware service representations. A contrastive learning framework is then introduced, constructing positive and negative sample pairs to enhance the separability of normal and abnormal patterns in the representation space. Furthermore, a temporal consistency constraint is designed to maintain representation stability across time steps and reduce the impact of short-term fluctuations and noise. The overall optimization combines contrastive loss and temporal consistency loss to ensure stable and reliable detection across multi-dimensional features. Experiments on public datasets systematically evaluate the method from hyperparameter, environmental, and data sensitivity perspectives. Results show that the proposed approach significantly outperforms existing methods on key metrics such as Precision, Recall, F1-Score, and AUC, while maintaining robustness under conditions of sparse labeling, monitoring noise, and traffic fluctuations. This study verifies the effectiveness of integrating dependency modeling with contrastive learning, provides a complete technical solution for cloud service anomaly detection, and demonstrates strong adaptability and stability in complex environments.

Problem

• Modeling complex dependencies in cloud service environments
• Detecting diverse anomaly patterns through contrastive learning
• Maintaining detection robustness under sparse labeling and noise

Innovation

• Uses contrastive learning to enhance anomaly pattern separability
• Models service dependencies with graph convolution for context
• Applies temporal consistency constraints to reduce noise impact