Federated learning has emerged recently as a promising solution for distributing machine tasks through modern networks of mobile devices. Recent studies have obtained lower bounds on the expected decrease in model loss that is achieved each round federated learning. However, convergence generally requires large number communication rounds, which induces delay training and costly terms network resources. In this paper, we propose fast-convergent algorithm, called <inline-formula...

Federated learning has generated significant interest, with nearly all works focused on a "star" topology where nodes/devices are each connected to central server. We migrate away from this architecture and extend it through the network dimension case there multiple layers of nodes between end devices Specifically, we develop multi-stage hybrid federated (MH-FL), intra- inter-layer model that considers as multi-layer cluster-based structure. MH-FL structures among in clusters, including...

Machine learning (ML) tasks are becoming ubiquitous in today's network applications. Federated has emerged recently as a technique for training ML models at the edge by leveraging processing capabilities across nodes that collect data. There several challenges with employing conventional federated contemporary networks, due to significant heterogeneity compute and communication exist devices. To address this, we advocate new paradigm called fog learning, which will intelligently distribute...

The conventional federated learning (FedL) architecture distributes machine (ML) across worker devices by having them train local models that are periodically aggregated a server. FedL ignores two important characteristics of contemporary wireless networks, however: (i) the network may contain heterogeneous communication/computation resources, while (ii) there be significant overlaps in devices' data distributions. In this work, we develop novel optimization methodology jointly accounts for...

Federated learning has emerged as a popular technique for distributing machine (ML) model training across the wireless edge. In this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">two timescale hybrid federated learning</i> ( <monospace xmlns:xlink="http://www.w3.org/1999/xlink">TT-HF</monospace> ), semi-decentralized architecture that combines conventional device-to-server communication paradigm with device-to-device (D2D)...

We consider unmanned aerial vehicle (UAV)-assisted wireless communication employing UAVs as relays to increase the throughput between a pair of transmitter and receiver. focus on developing effective methods position UAV(s) in presence interference environment, existence which makes problem non-trivial our methodology different from current art. study optimal planning, aims maximize (average) signal-to-interference-ratio (SIR) system, of: i) one major source interference, ii) stochastic...

In this paper, we study a new latency optimization problem for blockchain-based federated learning (BFL) in multi-server edge computing. system model, distributed mobile devices (MDs) communicate with set of servers (ESs) to handle both machine (ML) model training and block mining simultaneously. To assist the ML resource-constrained MDs, develop an offloading strategy that enables MDs transmit their data one associated ESs. We then propose decentralized aggregation solution at layer based...

We investigate training machine learning (ML) models across a set of geo-distributed, resource-constrained clusters devices through unmanned aerial vehicles (UAV) swarms. The presence time-varying data heterogeneity and computational resource inadequacy among device motivate four key parts our methodology: (i) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">stratified UAV swarms</i> leader, worker, coordinator UAVs, (ii)...

Federated learning (FedL) has emerged as a popular technique for distributing model training over set of wireless devices, via iterative local updates (at devices) and global aggregations the server). In this paper, we develop parallel successive (PSL), which expands FedL architecture along three dimensions: (i) Network, allowing decentralized cooperation among devices device-to-device (D2D) communications. (ii) Heterogeneity, interpreted at levels: (ii-a) Learning: PSL considers...

While network coverage maps continue to expand, many devices located in remote areas remain unconnected terrestrial communication infrastructures, preventing them from getting access the associated data-driven services. In this paper, we propose a ground-to-satellite cooperative federated learning (FL) methodology facilitate machine service management over regions. Our orchestrates satellite constellations provide following key functions during FL: (i) processing data offloaded ground...

Vehicular cloud (VC) platforms integrate heterogeneous and distributed resources of moving vehicles to offer timely cost-effective computing services. However, the dynamic nature VCs (i.e., limited contact duration among vehicles), caused by vehicles' mobility, poses unique challenges execution computation-intensive applications/tasks with a directed acyclic graph (DAG) structure, where each task consists multiple interdependent components (subtasks). In this paper, we study scheduling DAG...

Vehicular Clouds (VCs) are modern platforms for processing of computation-intensive tasks over vehicles. Such often represented as Directed Acyclic Graphs (DAGs) consisting interdependent vertices/subtasks and directed edges. However, efficient scheduling DAG VCs presents significant challenges, mainly due to the dynamic service provisioning vehicles within non-Euclidean representation tasks' topologies. In this paper, we propose a Graph neural network-Augmented Deep Reinforcement Learning...

Federated learning (FL) has emerged as a key technique for distributed machine (ML). Most literature on FL focused ML model training (i) single task/model, with (ii) synchronous scheme updating parameters, and (iii) static data distribution setting across devices, which is often not realistic in practical wireless environments. To address this, we develop DMA-FL considering dynamic multiple downstream tasks/models over an asynchronous update architecture. We first characterize convergence...

The rapid growth of AI-enabled Internet Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in literature on VEC-HFL vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial...

Fine-tuning large language models (LLMs) on devices is attracting increasing interest. Recent works have fused low-rank adaptation (LoRA) techniques with federated fine-tuning to mitigate challenges associated device model sizes and data scarcity. Still, the heterogeneity of computational resources remains a critical bottleneck: while higher-rank modules generally enhance performance, varying capabilities constrain LoRA's feasible rank range. Existing approaches attempting resolve this issue...

Future wireless networks must support emerging applications where environmental awareness is as critical data transmission. Integrated Sensing and Communication (ISAC) enables this vision by allowing base stations (BSs) to allocate bandwidth power mobile users (MUs) for communications cooperative sensing. However, resource allocation highly challenging due to: (i) dynamic demands from MUs supply BSs, (ii) the selfishness of BSs. To address these challenges, existing solutions rely on either...

Federated Learning (FL) offers a pioneering distributed learning paradigm that enables devices/clients to build shared global model. This model is obtained through frequent transmissions between clients and central server, which may cause high latency, energy consumption, congestion over backhaul links. To overcome these drawbacks, Hierarchical (HFL) has emerged, organizes into multiple clusters utilizes edge nodes (e.g., servers) for intermediate aggregations the server. Current research on...

Vehicular clouds (VCs) play a crucial role in the Internet-of-Vehicles (IoV) ecosystem by securing essential computing resources for wide range of tasks. This paPertackles intricacies resource provisioning dynamic VCs computation-intensive tasks, represented undirected graphs parallel processing over multiple vehicles. We model dynamics considering factors, including varying communication quality among vehicles, fluctuating capabilities uncertain contact duration and data exchange costs...

In this paper, we consider the optimal design of interlinks for an interdependent system networks. contrast to existing literature, explicitly exploit information intra-layer node degrees structures such that their robustness against cascading failures, triggered by randomized attacks, is maximized. Utilizing percolation theory-based equations relating network its degree sequence, characterize one-to-one structure, with complete interdependence and partial interdependence, under attack. We...

Applications of intelligent reflecting surfaces (IRSs) in wireless networks have attracted significant attention recently. Most the relevant literature is focused on single cell setting where a IRS deployed and perfect channel state information (CSI) assumed. In this work, we develop novel methodology for multi-IRS-assisted multi-cell uplink. We consider scenario which (i) channels are dynamic (ii) only partial CSI available at each base station (BS); specifically, scalar effective powers...

We investigate a transmission mechanism aiming to improve the data rate between base station (BS) and user equipment (UE) through deploying multiple relaying UAVs. consider effect of interference incurred by another established communication network, which makes our problem challenging different from state art. aim design 3D trajectories power allocation for UAVs maximize flow network while keeping on existing below threshold. utilize mobility feature evade (un)-intended caused...

The use of machine learning (ML) for cancer staging through medical image analysis has gained substantial interest across disciplines. When accompanied by the innovative federated (FL) framework, ML techniques can further overcome privacy concerns related to patient data exposure. Given frequent presence diverse modalities within records, leveraging FL in a multi-modal framework holds considerable promise staging. However, existing works on often presume that all data-collecting institutions...

Vehicular cloud computing has been emerged as a promising solution to fulfill users' demands on processing computation-intensive applications in modern driving environments. Such are commonly represented by graphs consisting of components and edges. However, encouraging vehicles share resources poses significant challenges owing selfishness. In this paper, an auction-based graph job allocation problem is studied vehicular cloud-assisted networks considering resource reutilization. Our goal...

This article investigates vehicular cloud (VC)-assisted task scheduling in an air-ground integrated network (AGVN), where tasks carried by unmanned aerial vehicles (UAVs) and resources of VCs are both modeled as graph structures. We consider a scenario which resource-limited UAVs carry set computation-intensive tasks, offloaded to resource-abundant for processing. formulate optimization problem jointly optimize the mapping between components vehicles, transmission powers UAVs, while...