Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems towards large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, democratized learning (Dem-AI) (Minh et al. 2020) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. The outlined principles are meant to provide a generalization of distributed learning that goes beyond existing mechanisms such as federated learning. Inspired from this philosophy, a novel distributed learning approach is proposed in this paper. The approach consists of a self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and corresponding learning mechanism. Subsequently, a hierarchical generalized learning problem in a recursive form is formulated and shown to be approximately solved using the solutions of distributed personalized learning problems and hierarchical generalized averaging mechanism. To that end, a distributed learning algorithm, namely DemLearn and its variant, DemLearn-P is proposed. Extensive experiments on benchmark MNIST and Fashion-MNIST datasets show that proposed algorithms demonstrate better results in the generalization performance of learning model at agents compared to the conventional FL algorithms. Detailed analysis provides useful configurations to further tune up both the generalization and specialization performance of the learning models in Dem-AI systems.
In this paper, the problem of delay minimization for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model parameters to a base station (BS) which aggregates the local FL models and broadcasts the aggregated FL model back to all the users. Since FL involves learning model exchanges between the users and the BS, both computation and communication latencies are determined by the required learning accuracy level, which affects the convergence rate of the FL algorithm. This joint learning and communication problem is formulated as a delay minimization problem, where it is proved that the objective function is a convex function of the learning accuracy. Then, a bisection search algorithm is proposed to obtain the optimal solution. Simulation results show that the proposed algorithm can reduce delay by up to 27.3% compared to conventional FL methods.
Internet of Things (IoT) services will use machine learning tools to efficiently analyze various types of data collected by IoT devices for inference, autonomy, and control purposes. However, due to resource constraints and privacy challenges, edge IoT devices may not be able to transmit their collected data to a central controller for training machine learning models. To overcome this challenge, federated learning (FL) has been proposed as a means for enabling edge devices to train a shared machine learning model without data exchanges thus reducing communication overhead and preserving data privacy. However, Google's seminal FL algorithm requires all devices to be directly connected with a central controller, which significantly limits its application scenarios. In this context, this paper introduces a novel FL framework, called collaborative FL (CFL), which enables edge devices to implement FL with less reliance on a central controller. The fundamentals of this framework are developed and then, a number of communication techniques are proposed so as to improve the performance of CFL. To this end, an overview of centralized learning, Google's seminal FL, and CFL is first presented. For each type of learning, the basic architecture as well as its advantages, drawbacks, and usage conditions are introduced. Then, three CFL performance metrics are presented and a suite of communication techniques ranging from network formation, device scheduling, mobility management, and coding is introduced to optimize the performance of CFL. For each technique, future research opportunities are also discussed. In a nutshell, this article will showcase how the proposed CFL framework can be effectively implemented at the edge of large-scale wireless systems such as the Internet of Things.
In this paper, the design of an optimal trajectory for an energy-constrained drone operating in dynamic network environments is studied. In the considered model, a drone base station (DBS) is dispatched to provide uplink connectivity to ground users whose demand is dynamic and unpredictable. In this case, the DBS's trajectory must be adaptively adjusted to satisfy the dynamic user access requests. To this end, a meta-learning algorithm is proposed in order to adapt the DBS's trajectory when it encounters novel environments, by tuning a reinforcement learning (RL) solution. The meta-learning algorithm provides a solution that adapts the DBS in novel environments quickly based on limited former experiences. The meta-tuned RL is shown to yield a faster convergence to the optimal coverage in unseen environments with a considerably low computation complexity, compared to the baseline policy gradient algorithm. Simulation results show that, the proposed meta-learning solution yields a 25% improvement in the convergence speed, and about 10% improvement in the DBS' communication performance, compared to a baseline policy gradient algorithm. Meanwhile, the probability that the DBS serves over 50% of user requests increases about 27%, compared to the baseline policy gradient algorithm.
In this paper, the problem of minimizing energy and time consumption for task computation and transmission is studied in a mobile edge computing (MEC)-enabled balloon network. In the considered network, each user needs to process a computational task in each time instant, where high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational abilities to process the tasks offloaded from their associated users. Since the data size of each user's computational task varies over time, the HABs must dynamically adjust the user association, service sequence, and task partition scheme to meet the users' needs. This problem is posed as an optimization problem whose goal is to minimize the energy and time consumption for task computing and transmission by adjusting the user association, service sequence, and task allocation scheme. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables each HAB to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the prediction of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real data of city cellular traffic from the OMNILab at Shanghai Jiao Tong University show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 16.1% compared to a conventional centralized method.
Due to the availability of huge amounts of data and processing abilities, current artificial intelligence (AI) systems are effective at solving complex tasks. However, despite the success of AI in different areas, the problem of designing AI systems that can truly mimic human cognitive capabilities such as artificial general intelligence, remains largely open. Consequently, many emerging cross-device AI applications will require a transition from traditional centralized learning systems towards large-scale distributed AI systems that can collaboratively perform multiple complex learning tasks. In this paper, we propose a novel design philosophy called democratized learning (Dem-AI) whose goal is to build large-scale distributed learning systems that rely on the self-organization of distributed learning agents that are well-connected, but limited in learning capabilities. Correspondingly, inspired from the societal groups of humans, the specialized groups of learning agents in the proposed Dem-AI system are selforganized in a hierarchical structure to collectively perform learning tasks more efficiently. As such, the Dem-AI learning system can evolve and regulate itself based on the underlying duality of two processes that we call specialized and generalized processes. In this regard, we present a reference design as a guideline to realize future Dem-AI systems, inspired by various interdisciplinary fields. Accordingly, we introduce four underlying mechanisms in the design such as plasticity-stability transition mechanism, self-organizing hierarchical structuring, specialized learning, and generalization. Finally, we establish possible extensions and new challenges for the existing learning approaches to provide better scalable, flexible, and more powerful learning systems with the new setting of Dem-AI.
In this paper, the problem of head movement prediction for virtual reality videos is studied. In the considered model, a deep learning network is introduced to leverage position data as well as video frame content to predict future head movement. For optimizing data input into this neural network, data sample rate, reduced data, and long-period prediction length are also explored for this model. Simulation results show that the proposed approach yields 16.1\% improvement in terms of prediction accuracy compared to a baseline approach that relies only on the position data.
In this paper, a novel framework is proposed to optimize the downlink multi-user communication of a millimeter wave base station, which is assisted by a reconfigurable intelligent reflector (IR). In particular, a channel estimation approach is developed to measure the channel state information (CSI) in real-time. First, for a perfect CSI scenario, the optimal precoding transmission and power allocation is derived so as to maximize the sum of downlink rates towards multiple users, followed by the optimization of IR reflection coefficient to enhance the upper bound of the downlink transmission. Next, in the imperfect CSI scenario, a distributional reinforcement learning (DRL) approach is proposed to learn the optimal IR reflection and maximize the expectation of downlink capacity. In order to model the transmission rate's probability distribution, a learning algorithm, based on quantile regression (QR), is developed, and the proposed QR-DRL method is proved to converge to a stable distribution of downlink transmission rate. Simulation results show that, in the error-free CSI scenario, the proposed transmission approach yields over 20% and 2-fold increase in the downlink sum-rate, compared with a fixed IR reflection scheme and direct transmission scheme, respectively. Simulation results also show that by increasing the number of IR components, the downlink rate can be improved faster than by increasing the number of antennas at the BS. Furthermore, under limited knowledge of CSI, simulation results show that the proposed QR-DRL method, which learns a full distribution of the downlink rate, yields a better prediction accuracy and improves the downlink rate by 10% for online deployments, compared with a Q-learning baseline.
The stringent requirements of mobile edge computing (MEC) applications and functions fathom the high capacity and dense deployment of MEC hosts to the upcoming wireless networks. However, operating such high capacity MEC hosts can significantly increase energy consumption. Thus, a BS unit can act as a self-powered BS. In this paper, an effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. First, a two-stage linear stochastic programming problem is formulated with the goal of minimizing the total energy consumption cost of the system while fulfilling the energy demand. Second, a semi-distributed data-driven solution is proposed by developing a novel multi-agent meta-reinforcement learning (MAMRL) framework to solve the formulated problem. In particular, each BS plays the role of a local agent that explores a Markovian behavior for both energy consumption and generation while each BS transfers time-varying features to a meta-agent. Sequentially, the meta-agent optimizes (i.e., exploits) the energy dispatch decision by accepting only the observations from each local agent with its own state information. Meanwhile, each BS agent estimates its own energy dispatch policy by applying the learned parameters from meta-agent. Finally, the proposed MAMRL framework is benchmarked by analyzing deterministic, asymmetric, and stochastic environments in terms of non-renewable energy usages, energy cost, and accuracy. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost (with 95.8% prediction accuracy), compared to other baseline methods.
Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition. However, due to the lack of continuous connections between the UAV swarm and ground base stations (BSs), using centralized ML will be challenging, particularly when dealing with a large volume of data. In this paper, a novel framework is proposed to implement distributed federated learning (FL) algorithms within a UAV swarm that consists of a leading UAV and several following UAVs. Each following UAV trains a local FL model based on its collected data and then sends this trained local model to the leading UAV who will aggregate the received models, generate a global FL model, and transmit it to followers over the intra-swarm network. To identify how wireless factors, like fading, transmission delay, and UAV antenna angle deviations resulting from wind and mechanical vibrations, impact the performance of FL, a rigorous convergence analysis for FL is performed. Then, a joint power allocation and scheduling design is proposed to optimize the convergence rate of FL while taking into account the energy consumption during convergence and the delay requirement imposed by the swarm's control system. Simulation results validate the effectiveness of the FL convergence analysis and show that the joint design strategy can reduce the number of communication rounds needed for convergence by as much as 35% compared with the baseline design.