Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

2025-10-23

AI Summary

To address the challenge of automatically recommending critical dimensions for cloud service monitoring, this paper constructs a production-oriented heterogeneous monitoring graph and proposes a Transformer-based multi-head attention model. The method models entity relationships via a heterogeneous graph, incorporates random walk paths to capture long-range dependencies, and employs a multi-task joint loss function to mitigate data sparsity. Its core innovation lies in the end-to-end integration of graph-structured priors with sequential attention mechanisms to rank dimension importance. Evaluated on a real-world industrial dataset, the model achieves a 43.1% improvement in Mean Reciprocal Rank (MRR) over state-of-the-art baselines. Industrial validation by the product team yields a practicality score of 4.5/5, and the solution has been deployed in a large-scale intelligent cloud monitoring system.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Plan Execution and Monitoring

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide insights on the usefulness of this feature as perceived by the cloud service owners and lessons learned from deployment. Specifically, we introduce the problem of recommending the optimal subset of attributes (dimensions) that should be tracked by an automated watchdog (monitor) for cloud services. To begin, we construct the monitor heterogeneous graph at production-scale. The interaction dynamics of these entities are often characterized by limited structural and engagement information, resulting in inferior performance of state-of-the-art approaches. Moreover, traditional methods fail to capture the dependencies between entities spanning a long range due to their homophilic nature. Therefore, we propose an attention-enhanced entity ranking model inspired by transformer architectures. Our model utilizes a multi-head attention mechanism to focus on heterogeneous neighbors and their attributes, and further attends to paths sampled using random walks to capture long-range dependencies. We also employ multi-faceted loss functions to optimize for relevant recommendations while respecting the inherent sparsity of the data. Empirical evaluations demonstrate significant improvements over existing methods, with our model achieving a 43.1% increase in MRR. Furthermore, product teams who consumed these features perceive the feature as useful and rated it 4.5 out of 5.

Problem

• Recommending optimal attributes for cloud service monitoring
• Addressing limited structural information in entity interactions
• Capturing long-range dependencies between heterogeneous entities

Innovation

• Attention-enhanced ranking model for entity recommendation
• Multi-head attention captures heterogeneous neighbor attributes
• Random walk paths model long-range dependencies