Graph-Structured Deep Learning Framework for Multi-task Contention Identification with High-dimensional Metrics

2026-01-28

AI Summary

This work proposes a multitask learning approach that integrates graph-structured modeling and task decoupling to address the challenge of identifying resource contention types in high-dimensional systems. By applying nonlinear transformations to extract dynamic features from high-dimensional metrics, the method fuses multisource information—including resource utilization, scheduling behaviors, and task loads—and employs a graph neural network to capture inter-metric dependencies. An adaptive multitask loss weighting strategy is further introduced to enhance the model’s discriminative power and stability in distinguishing complex contention patterns. Experimental results on public system trace datasets demonstrate that the proposed method significantly outperforms baseline approaches in accuracy, recall, precision, and F1 score, while maintaining robust performance across varying batch sizes, sample scales, and dimensionalities.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

This study addresses the challenge of accurately identifying multi-task contention types in high-dimensional system environments and proposes a unified contention classification framework that integrates representation transformation, structural modeling, and a task decoupling mechanism. The method first constructs system state representations from high-dimensional metric sequences, applies nonlinear transformations to extract cross-dimensional dynamic features, and integrates multiple source information such as resource utilization, scheduling behavior, and task load variations within a shared representation space. It then introduces a graph-based modeling mechanism to capture latent dependencies among metrics, allowing the model to learn competitive propagation patterns and structural interference across resource links. On this basis, task-specific mapping structures are designed to model the differences among contention types and enhance the classifier's ability to distinguish multiple contention patterns. To achieve stable performance, the method employs an adaptive multi-task loss weighting strategy that balances shared feature learning with task-specific feature extraction and generates final contention predictions through a standardized inference process. Experiments conducted on a public system trace dataset demonstrate advantages in accuracy, recall, precision, and F1, and sensitivity analyses on batch size, training sample scale, and metric dimensionality further confirm the model's stability and applicability. The study shows that structured representations and multi-task classification based on high-dimensional metrics can significantly improve contention pattern recognition and offer a reliable technical approach for performance management in complex computing environments.

Problem

• multi-task contention
• high-dimensional metrics
• contention identification
• system performance
• resource contention

Innovation

• graph-structured deep learning
• multi-task contention identification
• high-dimensional metrics
• task decoupling
• adaptive loss weighting