Progressive Supervision via Label Decomposition: An Long-Term and Large-Scale Wireless Traffic Forecasting Method

2025-01-09

AI Summary

Addressing the challenge of long-term, large-scale urban wireless traffic forecasting under strong non-stationarity and massive node scalability, this paper proposes Progressive Supervision via Label Decomposition (PSLD). To tackle these dual challenges, PSLD introduces a novel label decomposition-driven progressive supervision paradigm, designs a random subgraph sampling algorithm to reduce training complexity, and constructs a progressive deep architecture that synergistically integrates multi-granularity label decomposition with temporal graph neural networks. Evaluated on three large-scale real-world datasets, PSLD achieves average error reductions of 2%, 4%, and 11% over state-of-the-art methods, demonstrating significant improvements in forecasting accuracy. Furthermore, the authors release WTFlib—a unified, open-source benchmark library—to support reproducible evaluation and fair comparative analysis.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Long-term and Large-scale Wireless Traffic Forecasting (LL-WTF) is pivotal for strategic network management and comprehensive planning on a macro scale. However, LL-WTF poses greater challenges than short-term ones due to the pronounced non-stationarity of extended wireless traffic and the vast number of nodes distributed at the city scale. To cope with this, we propose a Progressive Supervision method based on Label Decomposition (PSLD). Specifically, we first introduce a Random Subgraph Sampling (RSS) algorithm designed to sample a tractable subset from large-scale traffic data, thereby enabling efficient network training. Then, PSLD employs label decomposition to obtain multiple easy-to-learn components, which are learned progressively at shallow layers and combined at deep layers to effectively cope with the non-stationary problem raised by LL-WTF tasks. Finally, we compare the proposed method with various state-of-the-art (SOTA) methods on three large-scale WT datasets. Extensive experimental results demonstrate that the proposed PSLD significantly outperforms existing methods, with an average 2%, 4%, and 11% performance improvement on three WT datasets, respectively. In addition, we built an open source library for WT forecasting (WTFlib) to facilitate related research, which contains numerous SOTA methods and provides a strong benchmark.Experiments can be reproduced through https://github.com/Anoise/WTFlib.

Problem

• Wireless Network Traffic Prediction
• Long-term Forecasting
• Network Management and Planning

Innovation

• PSLD
• RSS algorithm
• LL-WTF prediction