# M2FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices

arXiv: https://arxiv.org/abs/2605.16375 · HTML: https://mlsanity.com/paper/2605.16375/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 10 May 2026.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network](https://mlsanity.com/paper/2308.03200/) (2023)
- [The State-of-the-Art in Air Pollution Monitoring and Forecasting Systems using IoT, Big Data, and Machine Learning](https://mlsanity.com/paper/2304.09574/) (2023)
- [Enhancing Air Quality Monitoring: A Brief Review of Federated Learning Advances](https://mlsanity.com/paper/2504.02909/) (2025)
- [PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality](https://mlsanity.com/paper/2509.16519/) (2025)

## Abstract (arXiv)

Accurate air quality prediction is essential for public health, environmental monitoring, and industrial safety. However, most existing approaches rely on centralized learning paradigms, which introduce challenges related to scalability, privacy preservation, and communication overhead in distributed Internet of Things (IoT) environments. Moreover, current federated learning (FL) based solutions predominantly utilize unimodal data, limiting their capability to capture complex environmental patterns. To address these limitations, we propose M2FedAQI, a lightweight multimodal federated framework for decentralized Air Quality Index (AQI) prediction across heterogeneous edge devices. The proposed framework integrates visual and tabular modalities through a feature modulation based fusion mechanism that enables efficient cross-modal interaction while maintaining low computational overhead. M2FedAQI is evaluated on two benchmark datasets, PM25Vision and TRAQID, for both classification and regression tasks under centralized and federated settings. Experimental results demonstrate that M2FedAQI consistently outperforms existing approaches, achieving improvements of up to 11.0% in Accuracy, 3.53% in AUC, 12.2% in F1-score, and 18.0% in R2, while reducing MAE and RMSE by up to 25.4% and 20.4%, respectively, compared with the strongest baselines. Furthermore, deployment on heterogeneous edge devices demonstrates efficient resource utilization in terms of communication overhead, memory footprint, and computational cost. To enhance communication security, TLS-based authentication is incorporated to ensure secure client participation and protect the FL communication channel from unauthorized third-party access without modifying the underlying FL protocol.