Amin Farajzadeh

Amin Farajzadeh, Animesh Yadav, Omid Abbasi et al.

We propose a federated learning (FL) in stratosphere (FLSTRA) system, where a high altitude platform station (HAPS) facilitates a large number of terrestrial clients to collaboratively learn a global model without sharing the training data. FLSTRA overcomes the challenges faced by FL in terrestrial networks, such as slow convergence and high communication delay due to limited client participation and multi-hop communications. HAPS leverages its altitude and size to allow the participation of more clients with line-of-sight (LOS) links and the placement of a powerful server. However, handling many clients at once introduces computing and transmission delays. Thus, we aim to obtain a delay-accuracy trade-off for FLSTRA. Specifically, we first develop a joint client selection and resource allocation algorithm for uplink and downlink to minimize the FL delay subject to the energy and quality-of-service (QoS) constraints. Second, we propose a communication and computation resource-aware (CCRA-FL) algorithm to achieve the target FL accuracy while deriving an upper bound for its convergence rate. The formulated problem is non-convex; thus, we propose an iterative algorithm to solve it. Simulation results demonstrate the effectiveness of the proposed FLSTRA system, compared to terrestrial benchmarks, in terms of FL delay and accuracy.

Amin Farajzadeh, Melike Erol-Kantarci

In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal frequency-division multiple access (OFDMA) scheduling and power control strongly coupled across neighboring cells. We study distributed downlink resource management -- joint subcarrier scheduling and power allocation -- under interference coupling and long-term per-user quality-of-service (QoS) minimum-rate constraints. By using virtual-queue deficit weights to enforce long-term QoS, we develop FedCritic, a serverless federated multi-agent actor-critic framework with decentralized execution. Unlike centralized training with decentralized execution (CTDE) approaches that require centralized critic learning and joint trajectory aggregation, FedCritic federates the critic through lightweight gossip-based parameter averaging over the interference graph, enabling stable value estimation without a central coordinator while keeping policies local. Simulations in an interference-rich reuse-1 setting show that FedCritic improves mean signal-to-interference-plus-noise ratio (SINR) and cell-edge rate, increases network-wide average sum-rate and fairness relative to non-coordinated and CTDE baselines, and achieves more stable training with lower coordination overhead.

Amin Farajzadeh, Animesh Yadav, Halim Yanikomeroglu

The deployment of federated learning (FL) in non-terrestrial networks (NTN) that are supported by high-altitude platform stations (HAPS) offers numerous advantages. Due to its large footprint, it facilitates interaction with a large number of line-of-sight (LoS) ground clients, each possessing diverse datasets along with distinct communication and computational capabilities. The presence of many clients enhances the accuracy of the FL model and speeds up convergence. However, the variety of datasets among these clients poses a significant challenge, as it leads to pervasive non-independent and identically distributed (non-IID) data. The data non-IIDness results in markedly reduced training accuracy and slower convergence rates. To address this issue, we propose a novel weighted attribute-based client selection strategy that leverages multiple user-specific attributes, including historical traffic patterns, instantaneous channel conditions, computational capabilities, and previous-round learning performance. By combining these attributes into a composite score for each user at every FL round and selecting users with higher scores as FL clients, the framework ensures more uniform and representative data distributions, effectively mitigating the adverse effects of non-IID data. Simulation results corroborate the effectiveness of the proposed client selection strategy in enhancing FL model accuracy and convergence rate, as well as reducing training loss, by effectively addressing the critical challenge of data non-IIDness in large-scale FL system implementations.

Amin Farajzadeh, Animesh Yadav, Halim Yanikomeroglu

In the ever-expanding landscape of the IoT, managing the intricate network of interconnected devices presents a fundamental challenge. This leads us to ask: "What if we invite the IoT devices to collaboratively participate in real-time network management and IoT data-handling decisions?" This inquiry forms the foundation of our innovative approach, addressing the burgeoning complexities in IoT through the integration of NTN architecture, in particular, VHetNet, and an MT-HFL framework. VHetNets transcend traditional network paradigms by harmonizing terrestrial and non-terrestrial elements, thus ensuring expansive connectivity and resilience, especially crucial in areas with limited terrestrial infrastructure. The incorporation of MT-HFL further revolutionizes this architecture, distributing intelligent data processing across a multi-tiered network spectrum, from edge devices on the ground to aerial platforms and satellites above. This study explores MT-HFL's role in fostering a decentralized, collaborative learning environment, enabling IoT devices to not only contribute but also make informed decisions in network management. This methodology adeptly handles the challenges posed by the non-IID nature of IoT data and efficiently curtails communication overheads prevalent in extensive IoT networks. Significantly, MT-HFL enhances data privacy, a paramount aspect in IoT ecosystems, by facilitating local data processing and limiting the sharing of model updates instead of raw data. By evaluating a case-study, our findings demonstrate that the synergistic integration of MT-HFL within VHetNets creates an intelligent network architecture that is robust, scalable, and dynamically adaptive to the ever-changing demands of IoT environments. This setup ensures efficient data handling, advanced privacy and security measures, and responsive adaptability to fluctuating network conditions.