Shared Representation Learning for High-Dimensional Multi-Task Forecasting under Resource Contention in Cloud-Native Backends

2025-12-24

AI Summary

This paper addresses the high-dimensional, multi-task time-series forecasting challenge in cloud-native backend systems under highly dynamic workloads, coupled metrics, and parallel tasks—exacerbated by resource contention, service topology drift, and complex inter-service interactions. To this end, we propose a unified multi-task time-series forecasting framework. Its key contributions are: (1) a novel cross-task graph-structured propagation module explicitly designed to model resource contention; (2) a dynamic gating-based feature modulation mechanism that adaptively captures non-stationary system states; and (3) a multi-scale trend-perturbation joint modeling architecture integrated with shared encoding and state fusion. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches across multiple error metrics (e.g., MAE, RMSE), exhibits low hyperparameter sensitivity, and maintains strong robustness and high accuracy under challenging conditions—including missing data, bursty workloads, and topology changes.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This study proposes a unified forecasting framework for high-dimensional multi-task time series to meet the prediction demands of cloud native backend systems operating under highly dynamic loads, coupled metrics, and parallel tasks. The method builds a shared encoding structure to represent diverse monitoring indicators in a unified manner and employs a state fusion mechanism to capture trend changes and local disturbances across different time scales. A cross-task structural propagation module is introduced to model potential dependencies among nodes, enabling the model to understand complex structural patterns formed by resource contention, link interactions, and changes in service topology. To enhance adaptability to non-stationary behaviors, the framework incorporates a dynamic adjustment mechanism that automatically regulates internal feature flows according to system state changes, ensuring stable predictions in the presence of sudden load shifts, topology drift, and resource jitter. The experimental evaluation compares multiple models across various metrics and verifies the effectiveness of the framework through analyses of hyperparameter sensitivity, environmental sensitivity, and data sensitivity. The results show that the proposed method achieves superior performance on several error metrics and provides more accurate representations of future states under different operating conditions. Overall, the unified forecasting framework offers reliable predictive capability for high-dimensional, multi-task, and strongly dynamic environments in cloud native systems and provides essential technical support for intelligent backend management.

Problem

• Forecasting high-dimensional multi-task time series in cloud-native backends
• Modeling dependencies among nodes under resource contention and topology changes
• Adapting to non-stationary behaviors like sudden load shifts and resource jitter

Innovation

• Shared encoding structure for unified monitoring indicators representation
• Cross-task structural propagation module for modeling node dependencies
• Dynamic adjustment mechanism for adapting to non-stationary system behaviors