ADAMT: Adaptive distributed multi-task learning for efficient image recognition in Mobile Ad-hoc Networks

Abstract

Distributed machine learning in mobile adhoc networks faces significant challenges due to the limited computational resources of devices, non-IID data distribution, and dynamic network topology. Existing approaches often rely on centralized coordination and stable network conditions, which may not be feasible in practice. To address these issues, we propose an adaptive distributed multi-task learning framework called ADAMT for efficient image recognition in resource-constrained mobile ad hoc networks. ADAMT introduces three key innovations: (1) a feature expansion mechanism that enhances the expressiveness of local models by leveraging task-specific information; (2) a deep hashing technique that enables efficient on-device retrieval and multi-task fusion; and (3) an adaptive communication strategy that dynamically adjusts the model updating process based on network conditions and node reliability. The proposed framework allows each device to perform personalized model training on its local dataset while collaboratively updating the shared parameters with neighboring nodes. Extensive experiments on the ImageNet dataset demonstrate the superiority of ADAMT over state-of-the-art methods. ADAMT achieves a top-1 accuracy of 0.867, outperforming existing distributed learning approaches. Moreover, ADAMT significantly reduces the communication overhead and accelerates the convergence speed by 2.69 times compared to traditional distributed SGD. The adaptive communication strategy effectively balances the trade-off between model performance and resource consumption, making ADAMT particularly suitable for resource-constrained environments. Our work sheds light on the design of efficient and robust distributed learning algorithms for mobile adhoc networks and paves the way for deploying advanced machine learning applications on edge devices.