Distributed Learning Algorithm Research Articles

SFL-TUM: Energy efficient SFRL method for large scale AI model's task offloading in UAV-assisted MEC networks

The convergence of mobile edge computing (MEC) network with unmanned aerial vehicles (UAVs) presents an auspicious opportunity to revolutionize wireless communication and facilitate high-speed internet access in remote regions for mobile devices (MDs) as well as large scale artificial intelligence (AI) models. However, the substantial amount of data produced by the UAVs-assisted MEC network necessitates the integration of efficient distributed learning techniques in AI models. In recent times, distributed learning algorithms, including federated reinforcement learning (FRL) and split learning (SL), have been explored for the purpose of learning machine learning (ML) models that are distributed by sharing model parameters, as opposed to large raw data-sets as seen in traditional centralized learning algorithms. To implement the hybrid method, the model is first trained locally on each UAV-assisted MEC network using SL. Subsequently, the model parameters that have been encrypted are sent to a central server for federated averaging. Finally, after the model has been updated, it is distributed to each UAV-assisted MEC network for local fine-tuning. Our simulations indicate that the proposed split and federated reinforcement learning (SFRL) framework yields comparable high-test accuracy performance while consuming less energy compared to extant distributed learning algorithms. Furthermore, the SFRL algorithm efficiently realizes energy-efficient selection between the SL and FRL methods under different distributions. Numerical results shows that the proposed scheme improves the accuracy by 29.31% and reduced the energy consumption by around 67.34% and time delay by about 7.37%. as compared to the existing baseline schemes.

QoE‐driven multi‐UAV deployment scheme for emergency communication networks

AbstractWhen ground communication infrastructure within a region cannot be used for some reason, deploying unmanned aerial vehicle (UAV)‐mounted base stations is undoubtedly the most effective way to provide communication services. This paper investigates the problem of joint deployment and power allocation of multiple UAVs, where ground terminals (GTs) seek to maximize quality of experience (QoE). In the mixed line‐of‐sight and non‐line‐of‐sight environment, UAVs need to change position in order to collect channel information until deployment problem is solved. Moreover, only neighboring UAVs communicate with each other, which makes the problem more difficult to solve. In order to solve this problem, game theory is used to model this problem and design a distributed learning algorithm to maximize the QoE of all GTs in the entire system. Simulation results validate the effectiveness of the proposed learning algorithm in improving the QoE fairness and achieving the rapid deployment of UAVs.

A distributed learning based on robust diffusion SGD over adaptive networks with noisy output data

Outliers and noises are unavoidable factors that cause performance of the distributed learning algorithms to be severely reduced. Developing a robust algorithm is vital in applications such as system identification and forecasting stock market, in which noise on the desired signals may intensely divert the solutions. In this paper, we propose a Robust Diffusion Stochastic Gradient Descent (RDSGD) algorithm based on the pseudo-Huber loss function which can significantly suppress the effect of Gaussian and non-Gaussian noises on estimation performances in the adaptive networks. Performance and convergence behavior of RDSGD are assessed in presence of the α-stable and Mixed-Gaussian noises in the stationary and non-stationary environments. Simulation results show that the proposed algorithm can achieve both higher convergence rate and lower steady-state misadjustment than the conventional diffusion algorithms and several robust algorithms.

Multiobjective Optimization of Space–Air–Ground-Integrated Network Slicing Relying on a Pair of Central and Distributed Learning Algorithms

Multiobjective Optimization of Space–Air–Ground-Integrated Network Slicing Relying on a Pair of Central and Distributed Learning Algorithms

Distributed Bootstrap Simultaneous Inference for High-Dimensional Quantile Regression

Modern massive data with enormous sample size and tremendous dimensionality are usually impossible to process with a single machine. They are typically stored and processed in a distributed manner. In this paper, we propose a distributed bootstrap simultaneous inference for a high-dimensional quantile regression model using massive data. Meanwhile, a communication-efficient (CE) distributed learning algorithm is developed via the CE surrogate likelihood framework and ADMM procedure, which can handle the non-smoothness of the quantile regression loss and the Lasso penalty. We theoretically prove the convergence of the algorithm and establish a lower bound on the number of communication rounds ιmin that warrant statistical accuracy and efficiency. The distributed bootstrap validity and efficiency are corroborated by an extensive simulation study.

Battery-aware federated learning: Challenges and solutions

Smartphone battery life is a pivotal factor in consumers' purchasing decisions. Recent years have witnessed a surge in studies focusing on smartphone energy management, with data-driven energy management systems offering solutions to prolong battery life. Federated Learning (FL) emerges as a promising distributed learning algorithm, enabling wireless devices to upload locally trained models, fostering collaborative learning without exposing sensitive data. This paper explores the FL process, particularly the Federated Averaging (FedAvg) approach, which excels in scenarios with homogeneous data. In the era of burgeoning data generation, traditional cloud computing systems face limitations, driving the adoption of Edge Computing (EC), which processes data closer to its source, enhancing response times. To make FL efficient for e-commerce, resource constraints must be addressed. This involves techniques like local updates and model compression, which reduce communication overhead. However, FL brings challenges related to data distribution heterogeneity and privacy concerns. Solutions like differential privacy, encryption, and access control are discussed. In conclusion, this paper presents an overview of smartphone battery life, data-driven energy management, and the potential of FL, emphasizing its relevance in the age of EC. By addressing resource limitations and privacy issues, FL holds promise for efficient data processing.

Network Sliced Distributed Learning-as-a-Service for Internet of Vehicles Applications in 6G Non-Terrestrial Network Scenarios

In the rapidly evolving landscape of next-generation 6G systems, the integration of AI functions to orchestrate network resources and meet stringent user requirements is a key focus. Distributed Learning (DL), a promising set of techniques that shape the future of 6G communication systems, plays a pivotal role. Vehicular applications, representing various services, are likely to benefit significantly from the advances of 6G technologies, enabling dynamic management infused with inherent intelligence. However, the deployment of various DL methods in traditional vehicular settings with specific demands and resource constraints poses challenges. The emergence of distributed computing and communication resources, such as the edge-cloud continuum and integrated terrestrial and non-terrestrial networks (T/NTN), provides a solution. Efficiently harnessing these resources and simultaneously implementing diverse DL methods becomes crucial, and Network Slicing (NS) emerges as a valuable tool. This study delves into the analysis of DL methods suitable for vehicular environments alongside NS. Subsequently, we present a framework to facilitate DL-as-a-Service (DLaaS) on a distributed networking platform, empowering the proactive deployment of DL algorithms. This approach allows for the effective management of heterogeneous services with varying requirements. The proposed framework is exemplified through a detailed case study in a vehicular integrated T/NTN with diverse service demands from specific regions. Performance analysis highlights the advantages of the DLaaS approach, focusing on flexibility, performance enhancement, added intelligence, and increased user satisfaction in the considered T/NTN vehicular scenario.

Attack–Defense Confrontation Analysis and Optimal Defense Strategy Selection Using Hybrid Game Theoretic Methods

False data injection attacks are executed in the electricity markets of smart grid systems for financial benefits. The attackers can maximize their profits through modifying the estimated transmission power and changing the prices of market electricity. As a response, defenders need to minimize expected load losses and generator trips through load and power generation adjustments. The selection of strategies of the attacking and defending sides turns out to be a symmetric game process. This article proposes a hybrid game theory method for analyzing the attack–defense confrontation: firstly, a micro-grid-based power market model considering false data injection attacks is established using the Nash equilibrium method; secondly, the attack–defense game function is constructed and solved via the Stackelberg equilibrium algorithm. The Markov game algorithm and distributed learning algorithm are used to update equilibrium function; finally, a dynamic game behavior model of the two players is constructed through simulating the attack–defense probability. The evolutionary game method is used to select the optimal defense strategy for dynamic probability changes. Modified IEEE standard bus systems are illustrated to certify the effectiveness of the proposed model.

Distributed Online Learning Algorithm for Noncooperative Games Over Unbalanced Digraphs.

This article investigates constrained online noncooperative games (NGs) of multiagent systems over unbalanced digraphs, where the cost functions of players are time-varying and are gradually revealed to corresponding players only after decisions are made. Moreover, in the problem, the players are subject to local convex set constraints and time-varying coupling nonlinear inequality constraints. To the best of our knowledge, no result about online games with unbalanced digraphs has been reported, let alone constrained online games. To seek the variational generalized Nash equilibrium (GNE) of the game online, a distributed learning algorithm is proposed based on gradient descent, projection, and primal-dual methods. Under the algorithm, sublinear dynamic regrets and constraint violations are established. Finally, online electricity market games illustrate the algorithm.

A Distributed Learning Algorithm for Power Control in Energy Efficient IRS Assisted SISO NOMA Networks

A Distributed Learning Algorithm for Power Control in Energy Efficient IRS Assisted SISO NOMA Networks

Surface defect detection methods for industrial products with imbalanced samples: A review of progress in the 2020s

Industrial products typically lack defects in smart manufacturing systems, which leads to an extremely imbalanced task of recognizing surface defects. With this imbalanced sample distribution, machine learning and deep learning algorithms preferentially learn features from the majority classes, potentially leading to inaccurate results. Addressing the issue of sample imbalance has thus emerged as a critical area of research within the field of industrial intelligent manufacturing. This paper discusses the imbalanced sample problem of industrial product surface defect detection algorithms, and proposes the existence of "four imbalances and two uncertainties". It also summarizes the industrial product surface dataset and innovatively adds the imbalance rate comparison to the dataset. In this study, data re-sampling, data expansion, feature extraction and identification, and re-weighting of category weights are elaborated at the level of data and algorithm respectively. Additionally, the paper explores prospective directions for future research, including supervised and unsupervised learning, transfer learning, anomaly detection, quality prediction, and future challenges. It is hoped to lay a solid foundation for the more far-reaching development of smart manufacturing and surface defect detection methods. And provide some directions for the research of sample imbalance and long-tail problems.

Self-Organizing Democratized Learning: Toward Large-Scale Distributed Learning Systems.

Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems toward large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, democratized learning (Dem-AI) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. The outlined principles are meant to study a generalization in distributed learning systems that go beyond existing mechanisms such as federated learning (FL). Moreover, such learning systems rely on hierarchical self-organization of well-connected distributed learning agents who have limited and highly personalized data and can evolve and regulate themselves based on the underlying duality of specialized and generalized processes. Inspired by Dem-AI philosophy, a novel distributed learning approach is proposed in this article. The approach consists of a self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and corresponding learning mechanism. Subsequently, hierarchical generalized learning problems in recursive forms are formulated and shown to be approximately solved using the solutions of distributed personalized learning problems and hierarchical update mechanisms. To that end, a distributed learning algorithm, namely DemLearn, is proposed. Extensive experiments on benchmark MNIST, Fashion-MNIST, FE-MNIST, and CIFAR-10 datasets show that the proposed algorithm demonstrates better results in the generalization performance of learning models in agents compared to the conventional FL algorithms. The detailed analysis provides useful observations to further handle both the generalization and specialization performance of the learning models in Dem-AI systems.

Federated Deep Reinforcement Learning-Based Intelligent Dynamic Services in UAV-Assisted MEC

Unmanned Aerial Vehicles (UAVs)-assisted Multi-access Edge Computing (MEC) has emerged as a promising solution in B5G/6G networks. The high flexibility and seamless connectivity of UAVs make them well-suited for providing enhanced communications coverage and efficient computing support. Particularly in situations where ground facilities may be compromised or communication is unreliable. In this paper, we study joint dynamic service switching and resource allocation for multiple UAVs in MEC network. We consider the heterogeneity of tasks and UAVs and model the dynamic service process of UAVs as a sequential decision problem based on the Markovian decision process. To enable dynamic and intelligent UAV service, we first propose a centralized dynamic service algorithm DDBC based on deep reinforcement learning. However, given the training difficulties of the centralized algorithm, we propose a more promising distributed learning algorithm FLBF, which combines federated learning. We conduct extensive simulations to evaluate the effectiveness and advantages of the proposed algorithms. Our results show that both DDBC and FLBF can improve the model convergence speed by 50%, and reduce the system cost by 12.30% to 35.72% compared to comparative algorithms. Furthermore, simulations indicate that FLBF is well-suited for training models in UAV-assisted MEC networks.

Decentralized Parallel SGD Based on Weight-Balancing for Intelligent IoV

Training machine learning models in a decentralized way has attracted tremendous attention on intelligent Internet of Vehicles (IIoV). However, it is highly dynamic and asymmetric for the connections between vehicles in IIoV due to the mobility of vehicles and the complex communication environment, which poses great challenges on designing efficient distributed learning algorithms. To address this problem, we focus on the basic stochastic gradient descent (SGD) algorithm and propose a decentralized parallel SGD algorithm (DPSGD-WB) for the complex IIoV. The algorithm is based on weight-balancing to overcome the difficulty caused by the dynamic and asymmetric connectivity in IIoV. With rigorous analysis, we show that DPSGD-WB converges on the optimal rate of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$O(1/\sqrt{Kn})$</tex-math> </inline-formula> , where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$</tex-math> </inline-formula> is the number of vehicle terminals and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$</tex-math> </inline-formula> is the number of iterations. To the best of our knowledge, our proposed algorithm is the first known decentralized parallel SGD algorithm that can be implemented in asymmetric and dynamic intelligent IoV systems. Finally, extensive experiments demonstrate the efficacy of our algorithm.

Estimates on learning rates for multi-penalty distribution regression

This paper is concerned with functional learning by utilizing two-stage sampled distribution regression. We study a multi-penalty regularization algorithm for distribution regression in the framework of learning theory. The algorithm aims at regressing to real-valued outputs from probability measures. The theoretical analysis of distribution regression is far from maturity and quite challenging since only second-stage samples are observable in practical settings. In our algorithm, to transform information of distribution samples, we embed the distributions to a reproducing kernel Hilbert space HK associated with Mercer kernel K via mean embedding technique. One of the primary contributions of this work is the introduction of a novel multi-penalty regularization algorithm, which is able to capture more potential features of distribution regression. Optimal learning rates of the algorithm are obtained under mild conditions. The work also derives learning rates for distribution regression in the hard learning scenario fρ∉HK, which has not been explored in the existing literature. Moreover, we propose a new distribution-regression-based distributed learning algorithm to face large-scale data or information challenges arising from distribution data. The optimal learning rates are derived for the distributed learning algorithm. By providing new algorithms and showing their learning rates, the work improves the existing literature in various aspects.

Geospatial distribution and machine learning algorithms for assessing water quality in surface water bodies of Morocco

Surface waterbodies being primary source of water for human consumption are being investigated for its quality globally. This study evaluated water quality in three rivers (River Nfifikh, Hassar and El Maleh) of Mohammedia prefecture, Morocco in terms of heavy metals occurrence during two seasons of winter and spring. The heavy metals analyzed were cadmium, iron, copper, zinc, and lead. Heavy metal pollution index was derived to quantify water quality and pollution. Hazard quotient and carcinogenic risk were calculated to determine possible health risk. Modelling and prediction were performed using random forest, support vector machine and artificial neural network. The heavy metal concentration was lower in the winter season than in the spring season. Heavy metal pollution index (H.P.I.) was in the range of 1.5–2 during the winter season and 2–3 during the spring season. In the Nfifikh river, Cd2+ and Fe were the main polluting heavy metal. H.Q. was < 1 in all three rivers, which signified no adverse health effect from exposure to heavy metals. However, carcinogenic risk assessment revealed that 1 in every 100 people was susceptible to cancer during the life span of 70 years. Based on the control point reference, it was found that Mohammedia prefecture as river water was already contaminated before it entered the prefecture boundary. This was again validated with the water lagoon Douar El Marja which is located near the industrial zones of Mohammedia prefecture. Future studies are required to investigate pollution of rivers prior to their entry in Mohammedia prefecture to identify potential source and adopt mitigation measures accordingly.

Research and analysis of matrix multiplica-tion in distributed learning algorithms

Matrix multiplication have become increasingly important nowa-days, which is applied in many kinds of fields. In this case, the need to improve the speed and efficiency of matrix multiplication is in-creasing. In this paper, the author analyzes some relevant theories about matrix multiplication as well as the advantage and disad-vantage of some applications that based on matrix multiplication. It turns out that matrix multiplication has a lot of room for devel-opment in the future cause the current method still has many de-fects and is not perfect. For example, it will still take plenty of time to finish the process of matrix multiplication when the matrices are large in size. However, its gratifying that some improvements have been achieved, which can help to optimize the efficiency. In addi-tion, some advanced methods start to appear. For instance, the method of combining matrix multiplication with AI provides a new direction for future research and development. Consequently, it is predictable that a significant achievement to optimize matrix mul-tiplication will be made in the future.

Online Distributed Learning for Aggregative Games With Feedback Delays

This paper proposes a new aggregative game (AG) model with feedback delays. The strategies of players are selected from given strategy sets and subject to global nonlinear inequality constraints. Both cost functions and constrained functions of players are time-varying, which reflects the changing nature of environments. At each time, each player only has access to its strategy set information, and the information of its current cost function and current constrained function is unknown. Due to feedback delays, the feedback information of corresponding cost functions and constrained functions is not revealed to players immediately after the selection of strategies. It would take a period of time for players to observe their feedback information. To address such an AG problem, a distributed learning algorithm is proposed with the local information from their neighbors and the delayed feedback information from environments, and it is applicable to time-varying weighted digraphs. We find that the two metrics of the algorithm grow sub-linearly with respect to the learning time. A simulation example is given to illustrate the performance of the proposed algorithm.

Robust Mechanical Fault Diagnosis With Noisy Label Based on Multistage True Label Distribution Learning

Fault diagnosis is an essential means to ensure the regular operation of mechanical systems. The existing data-driven algorithms are developed based on the assumption that the given label is entirely correct. However, mislabeling is common, which often occurs in industrial applications. These methods will overfit these mislabeled samples, resulting in inferior generalization. To this end, this article proposes a novel multistage true label distribution learning algorithm. Specifically, based on the training characteristics of data-driven algorithms on noisy datasets, a novel multistage adversarial loss function (MSA-Loss) is proposed. MSA-Loss can make the model construct the true label distribution from noisy datasets, prevent the model from overfitting the noisy samples, and finally keep the model with good generalization. The proposed method can be easily applied to any existing data-driven algorithm to improve its performance on noisy datasets. Our method is verified on high-speed aeronautical bearing and motor datasets, which prove that MSA-Loss has an excellent performance in noisy label scenarios. It can significantly improve the potential of existing diagnostic models in practical industrial applications.

Sparse Bandit Learning Based Location Management for Space-Ground Integrated Networks

The Space-Ground Integrated Network (SGIN) concept constitutes a promising solution for providing seamless global coverage. However, the mobility of satellites and wireless terminals imposes unprecedented challenges on the location management in SGIN. We tackle this challenge by conceiving a split identifier (ID) and Network Address (NA) based design for providing natural mobility support, and characterize the ID-NA mapping allocation problem by exploiting the storage capacity of both Geostationary Earth Orbit Satellites (GEOSs) and Low Earth Orbiting Satellites (LEOSs) to form a spatially distributed binding resolution system and optimize the caching reward in each LEOS. By considering the large quantity of ID-NA mapping and the sparsity of popular mapping having positive mean caching rewards, we formulate the mapping allocation problem as a sparse Multi-Armed Bandit (MAB) learning procedure, where the mappings are treated as the arms and the LEOSs act as the players. A distributed learning algorithm, namely the Sparse Upper confidence bound based Learning aided Caching algorithm (SULC), is proposed for estimating the mean caching rewards of mappings and selecting the optimal mappings for caching. Moreover, we derive a sub-linear upper bound of the cumulative learning regret to prove the learning efficiency of the proposed SULC. Extensive simulations have been conducted to show that the proposed SULC can quickly identify the popular mappings and provide near-optimal content hit rates. In contrast with the existing solutions, SULC has higher caching rewards and can significantly reduce the cumulative regret after a short period of learning.