With the rise of Software-Defined Networking (SDN) for managing traffic and ensuring seamless operations across interconnected devices, challenges arise when SDN controllers share infrastructure with deep learning (DL) workloads. Resource contention between DL training and SDN operations, especially in latency-sensitive IoT environments, can degrade SDN's responsiveness and compromise network performance. Federated Learning (FL) helps address some of these concerns by decentralizing DL training to edge devices, thus reducing data transmission costs and enhancing privacy. Yet, the computational demands of DL training can still interfere with SDN's performance, especially under the continuous data streams characteristic of IoT systems. To mitigate this issue, we propose REDUS (Resampling for Efficient Data Utilization in Smart-Networks), a resampling technique that optimizes DL training by prioritizing misclassified samples and excluding redundant data, inspired by AdaBoost. REDUS reduces the number of training samples per epoch, thereby conserving computational resources, reducing energy consumption, and accelerating convergence without significantly impacting accuracy. Applied within an FL setup, REDUS enhances the efficiency of model training on resource-limited edge devices while maintaining network performance. In this paper, REDUS is evaluated on the CICIoT2023 dataset for IoT attack detection, showing a training time reduction of up to 72.6% with a minimal accuracy loss of only 1.62%, offering a scalable and practical solution for intelligent networks.

Artificial Intelligence (AI) applications on Internet of Things (IoT) networks often involve relaying generated data to a server for deep learning training, which poses security risks to users' data. Federated Learning (FL) offers a distributed model training paradigm in which local data are kept at the edge and locally trained models are exchanged and aggregated by a server over several rounds to produce a global model. While successful, standard FL algorithms do not support heterogeneous local model design, an essential requirement, especially for resource-limited edge devices. Recently, Knowledge Distillation-based FL algorithms have provided model-agnostic FL to enable clients to independently design their local model and share soft labels instead of model parameters. KD-based FL algorithms are computationally expensive due to additional distillation training. We propose Federated Learning with Selective Knowledge Distillation (FedSKD) to address the limitations of system heterogeneity; and computation and communication demands. We evaluate different aspects of the proposed algorithm relative to baseline FL algorithms. Results show that FedSKD incurs significantly less per-round computation time and communication overhead relative to the considered model-based and KD-based FL algorithms.

The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM’s ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.

Medical image segmentation is a crucial component of computer-aided diagnosis (CAD) systems, as it aids in identifying important areas in medical images. In order to achieve optimal segmentation results, it is important to preserve the resolution of the input image. The dilated convolution module was introduced to maintain resolution across layers of a deep convolutional neural network by increasing the receptive field exponentially while keeping the parameters increase linearly. However, one drawback of using dilated convolution is that it can result in local spatial resolution loss by increasing the sparsity of the kernel in checkboard patterns. This work proposes a double-dilated convolution module to maintain local spatial resolution in medical image segmentation tasks while having a large receptive field. The module is applied to tumor segmentation in breast cancer mammograms using the state-of-art Deeplabv3+ network. The study also evaluates the developed models with the Gradient weighted Class Activation Map (Grad-CAM) and compares the performance of lesion segmentation networks on mammogram screenings from the INBreast dataset before and after using the proposed dilation module. The results show that the proposed module effectively improves the segmentation performance.

Federated Learning (FL) has emerged as a powerful approach to facilitate the construction of centralized models without compromising the data privacy of multiple participants. However, conventional FL methodologies do not address system heterogeneity where each participant needs to independently design its own model, a prevalent requirement in Internet of Things (IoT) applications due to the heterogeneous nature of tasks and data. Knowledge Distillation-based FL algorithms tackle this limitation by exchanging soft labels instead of model weights, thus giving each client the ability to independently design its local model architecture. While FL is inherently private, studies have indicated that exploiting gradients for a few iterations can reveal sensitive training data. To protect against privacy attacks, FL algorithms employ Differential Privacy (DP) to guarantee privacy protection, which can be applied using Local Differential Privacy (LDP). In this paper, we elaborate on preserving clients' training data privacy in KD (Knowledge Distillation)-based FL using DP, providing both privacy and flexibility. We provide theoretical analysis to extend the privacy guarantee to exchanged updates. Experimental analysis is performed utilizing Human Activity Recognition (HAR) datasets with different modalities. The results obtained demonstrate the capacity of KD-based FL to maintain a robust utility-privacy balance. Furthermore, for the same DP protection level, the utility of models trained on images was severely reduced across all FL algorithms. This suggests that the modality and complexity of a dataset are important factors for shaping the utility-privacy tradeoff of DP.

Emerging Internet of Things (IoT) applications, such as sensor-based Human Activity Recognition (HAR) systems, require efficient machine learning solutions due to their resource-constrained nature which raises the need to design heterogeneous model architectures. Federated Learning (FL) has been used to train distributed deep learning models. However, standard federated learning (fedAvg) does not allow the training of heterogeneous models. Our work addresses the model and statistical heterogeneities of distributed HAR systems. We propose a Federated Learning via Augmented Knowledge Distillation (FedAKD) algorithm for heterogeneous HAR systems and evaluate it on a self-collected sensor-based HAR dataset. Then, Kullback-Leibler (KL) divergence loss is compared with Mean Squared Error (MSE) loss for the Knowledge Distillation (KD) mechanism. Our experiments demonstrate that MSE contributes to a better KD loss than KL. Experiments show that FedAKD is communication-efficient compared with model-dependent FL algorithms and outperforms other KD-based FL methods under the i.i.d. and non-i.i.d. scenarios.

As 5G and beyond networks continue to proliferate, intelligent monitoring systems are becoming increasingly prevalent. However, geographically isolated regions with sparse populations still face difficulties in accessing these technologies due to infrastructure deployment challenges. Additionally, the high cost and unreliability of satellite Internet services make them less appealing. This paper studies the challenges of drone-aided networks and presents a communication-efficient Federated Learning (FL) system on a drone-aided Internet of Things (IoT) network to facilitate health analysis in rural areas over LoRa wireless links. The proposed approach consists of two primary components. Firstly, optimizing the drone’s trajectory is theoretically formulated as a modified version of the Traveling Salesman Problem (TSP), with the Self-Organizing Map (SOM) algorithm employed for effective route planning. Secondly, the Knowledge Distillation (KD)-based FL algorithm is utilized to reduce communication overhead by leveraging soft labels. The quality of drone routes generated by the SOM is evaluated on multi-scale maps with pre-determined optimal paths. The experiments reveal SOM’s ability to accurately represent node topologies and yield cost-effective Hamiltonian cycles. The KD-based FL proves to be more efficient in terms of communication than FedAvg as the former exchanges soft labels while the latter exchanges model weights, thus reducing drone waiting time and battery consumption. We showcase the performance of our KD-based FL algorithm using Human Activity Recognition (HAR) datasets, illustrating a communication-efficient alternative for distributed learning, offering competitive performance leveraging a shared dataset for knowledge transfer among IoT devices.