# Dual Attention-Based Federated Learning for Wireless Traffic Prediction

arXiv: https://arxiv.org/abs/2110.05183 · HTML: https://mlsanity.com/paper/2110.05183/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2021.

## Built on by (most cited first, 18 of 18)

- [TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature](https://mlsanity.com/paper/2205.12784/) (2022)
- [Poisoning Attacks on Federated Learning-based Wireless Traffic Prediction](https://mlsanity.com/paper/2404.14389/) (2024)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach](https://mlsanity.com/paper/2404.03702/) (2024)
- [Towards Energy-Aware Federated Traffic Prediction for Cellular Networks](https://mlsanity.com/paper/2309.10645/) (2023)
- [Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning](https://mlsanity.com/paper/2505.19263/) (2025)
- [Survey of Federated Learning Models for Spatial-Temporal Mobility Applications](https://mlsanity.com/paper/2305.05257/) (2023)
- [Preserving Data Privacy for ML-driven Applications in Open Radio Access Networks](https://mlsanity.com/paper/2402.09710/) (2024)
- [Clustered Scheduling and Communication Pipelining For Efficient Resource Management Of Wireless Federated Learning](https://mlsanity.com/paper/2206.07631/) (2022)
- [Distributed Learning for Wi-Fi AP Load Prediction](https://mlsanity.com/paper/2405.05140/) (2024)
- [FedASTA: Federated adaptive spatial-temporal attention for traffic flow prediction](https://mlsanity.com/paper/2405.13090/) (2024)
- [Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation](https://mlsanity.com/paper/2412.08460/) (2024)
- [A Dynamic Temporal Self-attention Graph Convolutional Network for Traffic Prediction](https://mlsanity.com/paper/2302.10428/) (2023)
- [Federated Radio Frequency Fingerprinting with Model Transfer and Adaptation](https://mlsanity.com/paper/2302.11418/) (2023)
- [Regional Correlation Aided Mobile Traffic Prediction with Spatiotemporal Deep Learning](https://mlsanity.com/paper/2312.06279/) (2023)
- [Federated Learning with Graph-Based Aggregation for Traffic Forecasting](https://mlsanity.com/paper/2507.09805/) (2025)
- [U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications](https://mlsanity.com/paper/2601.06867/) (2026)
- [F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting](https://mlsanity.com/paper/2608.09082/) (2026)

## Abstract (arXiv)

Wireless traffic prediction is essential for cellular networks to realize intelligent network operations, such as load-aware resource management and predictive control. Existing prediction approaches usually adopt centralized training architectures and require the transferring of huge amounts of traffic data, which may raise delay and privacy concerns for certain scenarios. In this work, we propose a novel wireless traffic prediction framework named textitDual Attention-Based Federated Learning (FedDA), by which a high-quality prediction model is trained collaboratively by multiple edge clients. To simultaneously capture the various wireless traffic patterns and keep raw data locally, FedDA first groups the clients into different clusters by using a small augmentation dataset. Then, a quasi-global model is trained and shared among clients as prior knowledge, aiming to solve the statistical heterogeneity challenge confronted with federated learning. To construct the global model, a dual attention scheme is further proposed by aggregating the intra- and inter-cluster models, instead of simply averaging the weights of local models. We conduct extensive experiments on two real-world wireless traffic datasets and results show that FedDA outperforms state-of-the-art methods. The average mean squared error performance gains on the two datasets are up to 10% and 30%, respectively.