MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction

2025/05/26 by Hui Ma, Kai Yang, Ma, Hui +1 · 1 citation
Engineering · #Advanced Data and IoT Technologies #Artificial Intelligence (cs.AI) #Energy Load and Power Forecasting #FOS: Computer and information sciences #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI) #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2505.21553

openalex publication_date 2025/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Network traffic prediction techniques have attracted much attention since they are valuable for network congestion control and user experience improvement. While existing prediction techniques can achieve favorable performance when there is sufficient training data, it remains a great challenge to make accurate predictions when only a small amount of training data is available. To tackle this problem, we propose a deep learning model, entitled MetaSTNet, based on a multimodal meta-learning framework. It is an end-to-end network architecture that trains the model in a simulator and transfers the meta-knowledge to a real-world environment, which can quickly adapt and obtain accurate predictions on a new task with only a small amount of real-world training data. In addition, we further employ cross conformal prediction to assess the calibrated prediction intervals. Extensive experiments have been conducted on real-world datasets to illustrate the efficiency and effectiveness of MetaSTNet.

Citations

• Cellular Traffic Prediction via Deep State Space Models with Attention Mechanism
• Neural-Sim: Learning to Generate Training Data with NeRF
• conformalInference.multi and conformalInference.fd: Twin Packages for Conformal Prediction
• Conformal prediction beyond exchangeability
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• Understanding Domain Randomization for Sim-to-real Transfer
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
• Locally Valid and Discriminative Prediction Intervals for Deep Learning Models
• Recent Advances and Trends in Multimodal Deep Learning: A Review
• Few-shot Conformal Prediction with Auxiliary Tasks
• A review of uncertainty quantification in deep learning: Techniques, applications and challenges
• Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled\n Wireless Networks: A Tutorial
• Bilevel Optimization: Convergence Analysis and Enhanced Design
• Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
• Meta-Learning in Neural Networks: A Survey
• Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks
• Meta-learning framework with applications to zero-shot time-series\n forecasting
• DeepAuto: A Hierarchical Deep Learning Framework for Real-Time Prediction in Cellular Networks
• Predictive inference with the jackknife+
• Conformalized Quantile Regression
• Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
• Learning To Simulate
• Attention Is All You Need
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Domain Randomization for Transferring Deep Neural Networks from\n Simulation to the Real World
• Semi-Supervised Classification with Graph Convolutional Networks
• Distribution-Free Predictive Inference For Regression

Cited by

• UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
• Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning

Related

• Hyper-parameter Optimization for Wireless Network Traffic Prediction Models with A Novel Meta-Learning Framework
• STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction
• User Traffic Prediction for Proactive Resource Management:\n Learning-Powered Approaches
• On the road to more accurate mobile cellular traffic predictions
• Causally-Aware Spatio-Temporal Multi-Graph Convolution Network for Accurate and Reliable Traffic Prediction