M$^2$FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices

arXiv cs.LG Papers
multimodal federated-learning air-quality edge-computing iot privacy-preserving

Summary

Proposes M²FedAQI, a lightweight multimodal federated learning framework for air quality prediction across heterogeneous edge devices, achieving significant improvements over baselines on benchmark datasets.

arXiv:2605.16375v1 Announce Type: new Abstract: 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 M$^2$FedAQI, 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. M$^2$FedAQI is evaluated on two benchmark datasets, PM25Vision and TRAQID, for both classification and regression tasks under centralized and federated settings. Experimental results demonstrate that M$^2$FedAQI 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 $R^2$, 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.
Original Article
View Cached Full Text

Cached at: 05/19/26, 06:42 AM 

# M$^2$FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices
Source: [https://arxiv.org/abs/2605.16375](https://arxiv.org/abs/2605.16375)
[View PDF](https://arxiv.org/pdf/2605.16375)

> Abstract: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 M$^2$FedAQI, 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\. M$^2$FedAQI is evaluated on two benchmark datasets, PM25Vision and TRAQID, for both classification and regression tasks under centralized and federated settings\. Experimental results demonstrate that M$^2$FedAQI 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 $R^2$, 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\.

## Submission history

From: Tamoghna Ojha \[[view email](https://arxiv.org/show-email/c3c3195f/2605.16375)\] **\[v1\]**Sun, 10 May 2026 20:21:49 UTC \(2,998 KB\)

Similar Articles

Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices

arXiv cs.LG

The paper introduces MESH-FL, an entropy-guided matrix product state compression framework for multimodal federated learning on edge devices. It adaptively allocates compression ranks per layer and modality, achieving up to 56.8× compression and 2.01% final accuracy improvement over uncompressed FedAvg on a heterogeneous Raspberry Pi cluster.

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

arXiv cs.LG

This paper proposes FedMPO, a robust federated multimodal graph learning method that addresses modality heterogeneity and missing modalities through topology-aware cross-modal generation, missing-aware expert routing, and reliability-aware aggregation, achieving performance gains on multiple datasets.

FedQHD: Closed-Form Function-Space Federated Reinforcement Learning

arXiv cs.LG

This paper proposes FedQHD, a novel federated Q-learning method using hyperdimensional random-feature state encoders with linear readouts to enable closed-form function-space aggregation, addressing the federation gap due to heterogeneous client encoders.

Federated Foundation Models over Vehicular Networks

arXiv cs.LG

This paper presents a vision for integrating multi-modal multi-task federated foundation models (M3T FedFMs) into vehicular networks, discussing training principles, use cases, challenges, and a case study on the Waymo Open Dataset.