Federated Learning Model Research Articles

Federated Learning Incentive Mechanism Design via Enhanced Shapley Value Method

Federated learning (FL) is an emerging collaborative machine learning method. In FL processing, the data quality shared by users directly affects the accuracy of the federated learning model, and how to encourage more data owners to share data is crucial. In other words, how to design a good incentive mechanism is the key problem in FL. In this paper, we propose an incentive mechanism based on the enhanced Shapley value method for FL. In the proposed mechanism, the enhanced Shapley value method is proposed to measure income distribution, which takes multiple influence factors as weights. The analytic hierarchy process (AHP) is used to find the corresponding weight value of the influence factors. Finally, the numerical experiments are carried to verify the performance of the proposed incentive mechanism. The results show that compared with the Shapley value method considering the single factor, the income distribution of all participants can better reflect multiple factor contribution when using the enhanced Shapley value method.

Trust-based federated learning for network anomaly detection

With the rapid development of social networks and the massive popularity of intelligent mobile terminals, network anomaly detection is becoming increasingly important. In daily work and life, edge nodes store a large number of network local connection data and audit data, which can be used to analyze network abnormal behavior. With the increasingly close network communication, the amount of network connection and other related data collected by each network terminal is increasing. Machine learning has become a classification method to analyze the features of big data in the network. Face to the problems of excessive data and long response time for network anomaly detection, we propose a trust-based Federated learning anomaly detection algorithm. We use the edge nodes to train the local data model, and upload the machine learning parameters to the central node. Meanwhile, according to the performance of edge nodes training, we set different weights to match the processing capacity of each terminal which will obtain faster convergence speed and better attack classification accuracy. The user’s private information will only be processed locally and will not be uploaded to the central server, which can reduce the risk of information disclosure. Finally, we compare the basic federated learning model and TFCNN algorithm on KDD Cup 99 dataset and MNIST dataset. The experimental results show that the TFCNN algorithm can improve accuracy and communication efficiency.

Cell Based Raft Algorithm for Optimized Consensus Process on Blockchain in Smart Data Market

Due to the explosive increase in IoT devices and traffic, big data is developing into smart data that helps the data science experts understand human activities, through the relationship between mobility and resource application of the users in public spaces. For example, smart data markets help to predict crimes or understand the infection the cause of COVID-19 infections. For these smart services, the users agree to the privacy policy so that the personal and sensitive information can be collected by a third party. But the conditions of the privacy policy do not specify whether the information of the users can be tracked. To ensure data transparency, many systems are applying consortium/private blockchains with raft algorithm. The raft algorithm requires nodes to check countless messages for a single transaction. Eventually, as the number of nodes increases, the overall system degradation is derived from the burden of the leader node. This paper proposes a method to process the collected transactions by dividing a certain amount of transactions into cells, without any extra protocol. The proposed scheme also uses the federated learning model with high accuracy and data privacy, in order to determine the optimized cell size in a blockchain system that should lead to consensus on multiple servers. Therefore, the proposed CBR(Cell-based Raft) consensus algorithm proposes a protocol that reduces the number of messages, without interfering with the concept of the existing raft algorithm, in order to maintain stable throughput in the smart data market where massive transactions occur.

Multi-Agent Deep Q-Networks for Efficient Edge Federated Learning Communications in Software-Defined IoT

Federated learning (FL) activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes. However, in large-scale heterogeneous Internet of Things (IoT) cellular networks, massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly. This paper introduces the system model of converging software-defined networking (SDN) and network functions virtualization (NFV) to enable device/resource abstractions and provide NFV-enabled edge FL (eFL) aggregation servers for advancing automation and controllability. Multi-agent deep Q-networks (MADQNs) target to enforce a self-learning softwarization, optimize resource allocation policies, and advocate computation offloading decisions. With gathered network conditions and resource states, the proposed agent aims to explore various actions for estimating expected long-term rewards in a particular state observation. In exploration phase, optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections. Action-based virtual network functions (VNF) forwarding graph (VNFFG) is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure (NFVI). The proposed scheme indicates deficient allocation actions, modifies the VNF backup instances, and reallocates the virtual resource for exploitation phase. Deep neural network (DNN) is used as a value function approximator, and epsilon-greedy algorithm balances exploration and exploitation. The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy. Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service (QoS) performance metrics, including packet drop ratio, packet drop counts, packet delivery ratio, delay, and throughput.

Toward Efficient Hierarchical Federated Learning Design Over Multi-Hop Wireless Communications Networks

Federated learning (FL) has recently received considerable attention and is becoming a popular machine learning (ML) framework that allows clients to train machine learning models in a decentralized fashion without sharing any private dataset. In the FL framework, data for learning tasks are acquired and processed locally at the edge node, and only the updated ML parameters are transmitted to the central server for aggregation. However, because local FL parameters and the global FL model are transmitted over wireless links, wireless network performance will affect FL training performance. In particular, the number of resource blocks is limited; thus, the number of devices participating in FL is limited. Furthermore, edge nodes often have substantial constraints on their resources, such as memory, computation power, communication, and energy, severely limiting their capability to train large models locally. This paper proposes a two-hop communication protocol with a dynamic resource allocation strategy to investigate the possibility of bandwidth allocation from a limited network resource to the maximum number of clients participating in FL. In particular, we utilize an ordinary hierarchical FL with an adaptive grouping mechanism to select participating clients and elect a leader for each group based on its capability to upload the aggregated parameters to the central server. Our experimental results demonstrate that the proposed solution outperforms the baseline algorithm in terms of communication cost and model accuracy.

An Optimized Multi-Task Learning Model for Disaster Classification and Victim Detection in Federated Learning Environments

Disaster classification and victim detection are two important tasks in enabling efficient rescue operations. In this paper, we propose a multi-task learning (MTL) model which accomplishes these two tasks simultaneously. The idea is to attach one pruned head model to another backbone network. We mathematically pinpoint the optimal branching location and the depth of the pruned head model. Apart from the decoupled task training capability, the MTL model offers lesser memory requirements (12.8 MB saving) and better disaster classification accuracy (1-2% gain), while preserving the same detection performance (0.694 of average precision (AP)), as compared to the traditional method. Such advantages of flexibility, speed and accuracy facilitate the large-scale deployment of Internet of Things (IoT) applications, where we explore the potential of federated learning (FL) and active learning (AL). Given the high ambiguity within disaster images, a modified version of AL-based technique is introduced. For realistic implementation, production-ready OpenFL and OpenVINO tools are adopted to update the global FL model and to optimize the trained model, respectively. Experiment results are promising: the FL-based techniques are comparable to or better than their centralized learning (CL) counterparts. Also, our application portability is demonstrated via different hardware such as CPU and Raspberry Pi.

Federated Learning Approach for Measuring the Response of Brain Tumors to Chemotherapy

Brain tumor is a fatal disease and one of the major causes of rising death rates in adults. Predicting methylation of the O6-Methylguanine-DNA Methyltransferase (MGMT) gene status utilizing Magnetic resonance imaging (MRI) imaging is highly important since it is a predictor of brain tumor responses to chemotherapy, which reduces the number of needed surgeries. Deep Learning (DL) approaches became powerful in extracting meaningful relationships and making accurate predictions. DL-based models require a large database and accessing or transferring patient data to train the model. Federated machine learning has recently gained popularity, as it offers practical solutions for data privacy, centralized computation, and high computing power. This study aims to investigate the feasibility of federated learning (FL) by developing a FL-based approach to predict MGMT promoter methylation status using the BraTs2021 dataset for the four sequence types, (Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted (T1w), T1-weighted Gadolinium Post Contrast (T1wCE/T1Gd), and T2-weighted (T2w)) MRI images. The FL model compared to the DL-based and the experimental results show that even with imbalanced and heterogeneous datasets, the FL approach reached the training model to 99.99% of the model quality achieved with centralized data after 300 communication rounds between 10 institutions using OpenFl framework and the improved EfficentNet-B3 neural network architecture.

FedMarket: A Cryptocurrency Driven Marketplace for Mobile Federated Learning Services

Federated learning (FL) enables the training of a shared collaborative machine learning model while keeping all the confidential training data on distributed devices. The FL state-of-the-art considers a monopolist FL task publisher. However, we present a FL marketplace where multiple FL task publishers and mobile devices co-exist for a set of diverse and varying learning tasks. Mobile devices participating in the training of FL models provides pay-as-you-go (i.e. using blockchain-based cryptocurrencies) FL training services to the FL task publishers. In the proposed framework, multiple FL task publishers may compete with each other and the participating workers (i.e. mobile devices) can choose one FL task publisher over another for participation in the training of a global model. We utilize code offloading for enabling customized FL pipelines in mobile devices and mitigating the model heterogeneity inherent in varying and changing FL tasks published by the task publishers. Experimental results indicate the efficacy of the proposed framework.

Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions

The smart healthcare system has improved the patients quality of life (QoL), where the records are being analyzed remotely by distributed stakeholders. It requires a voluminous exchange of data for disease prediction via the open communication channel, i.e., the Internet to train artificial intelligence (AI) models efficiently and effectively. The open nature of communication channels puts data privacy at high risk and affects the model training of collected data at centralized servers. To overcome this, an emerging concept, i.e., federated learning (FL) is a viable solution. It performs training at client nodes and aggregates their results to train the global model. The concept of local training preserves the privacy, confidentiality, and integrity of the patient’s data which contributes effectively to the training process. The applicability of FL in the healthcare domain has various advantages, but it has not been explored to its extent. The existing surveys majorly focused on the role of FL in diverse applications, but there exists no detailed or comprehensive survey on FL in healthcare informatics (HI). We present a relative comparison of recent surveys with the proposed survey. To strengthen healthcare data privacy and increase the QoL of patients, we proposed an FL-based layered healthcare informatics architecture along with the case study on FL-based electronic health records (FL-EHR). We discuss the emerging FL models, and present the statistical and security challenges in FL adoption in medical setups. Thus, the review presents useful insights for both academia and healthcare practitioners to investigate FL application in HI ecosystems.

A Differentially Private Federated Learning Model against Poisoning Attacks in Edge Computing

Federated learning is increasingly popular, as it allows us to circumvent challenges due to data islands, by training a global model using data from one or more data owners/sources. However, in edge computing, resource-constrained end devices are vulnerable to be compromised and abused to facilitate poisoning attacks. Privacy-preserving is another important property to consider when dealing with sensitive user data on end devices. Most existing approaches only consider either defending against poisoning attacks or supporting privacy, but not both properties simultaneously. In this paper, we propose a differentially private federated learning model against poisoning attacks, designed for edge computing deployment. First, we design a weight-based algorithm to perform anomaly detection on the parameters uploaded by end devices in edge nodes, which improves detection rate using only small-size validation datasets and minimizes the communication cost. Then, differential privacy technology is leveraged to protect the privacy of both data and model in an edge computing setting. We also evaluate and compare the detection performance in the presence of random and customized malicious end devices with the state-of-the-art, in terms of attack resiliency, communication and computation costs. Experimental results demonstrate that our scheme can achieve an optimal tradeoff between security, efficiency and accuracy.

Sandbox Computing: A Data Privacy Trusted Sharing Paradigm via Blockchain and Federated Learning

As a new trusted data sharing pattern with privacy protection, the integration mechanism of blockchain and Federated Learning has attracted extensive attention. Generally, this mechanism uses blockchain technology to supervise the original data and calculation results, which ignores the supervision of the Federated Learning model and computing process. Therefore, we introduce the concepts of the sandbox and state channel to construct a new data privacy sharing paradigm via Blockchain and Federated Learning. Under this paradigm, we use state channel to connect Blockchain and Federated Learning. And state channel is used to create a “trusted sandbox” to instantiate Federated Learning tasks in the trustless edge computing environment. Meanwhile, we also mainly solve problems about data privacy sharing in Federated Learning and system performance degradation caused by data quality. The simulation results show that the proposed method has better performance and efficiency than the traditional data sharing method.

Application of Federated Learning Algorithm Based on K-Means in Electric Power Data

Accurate electricity forecasting is the key basis for guiding the power sector to arrange operation plans and guaranteeing the profitability of electric power companies. However, with the increasing demand of enterprises and departments for data security, the phenomenon of “Isolated Data Island” becomes more and more serious, resulting in the accuracy loss of the traditional electricity prediction model. Federated learning, as an emerging artificial intelligence technology, is designed to ensure data privacy while carrying out efficient machine learning, which provides a new way to solve the problem of “Isolated Data Island” in terms of electricity forecasting. Nonetheless, due to the popularity of smart meters, the collected electricity data presents the characteristics of uneven distribution and huge data volume, so it is difficult to apply the electric quantity prediction model generated only by federated learning in practice. To solve this problem, a clustering federated learning method (C-FL) is proposed to protect data privacy while improving the accuracy of power prediction. Firstly, C-FL uses K-means algorithm to cluster power data locally in power enterprises, and then builds accurate power forecasting models for each class of power data combined with other local clients through federated learning. A large number of experimental results show that the clustering federated learning method proposed in this paper is superior to the existing federated learning models in terms of the accuracy of electric power forecasting.

DistFL

Federated learning (FL) has emerged as an effective solution to decentralized and privacy-preserving machine learning for mobile clients. While traditional FL has demonstrated its superiority, it ignores the non-iid (independently identically distributed) situation, which widely exists in mobile scenarios. Failing to handle non-iid situations could cause problems such as performance decreasing and possible attacks. Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models. However, previous techniques overlook the root causes for the "symptoms": blindly aggregating models with the non-iid distributions. In this paper, we try to fundamentally address the issue by decomposing the overall non-iid situation into several iid clusters and conducting aggregation in each cluster. Specifically, we propose DistFL, a novel framework to achieve automated and accurate Distribution-aware Federated Learning in a cost-efficient way. DistFL achieves clustering via extracting and comparing the distribution knowledge from the uploaded models. With this framework, we are able to generate multiple personalized models with distinctive distributions and assign them to the corresponding clients. Extensive experiments on mobile scenarios with popular model architectures have demonstrated the effectiveness of DistFL.

A lightweight federated learning based privacy preserving B5G pandemic response network using unmanned aerial vehicles: A proof-of-concept

The concept of an intelligent pandemic response network is gaining momentum during the current novel coronavirus disease (COVID-19) era. A heterogeneous communication architecture is essential to facilitate collaborative and intelligent medical analytics in the fifth generation and beyond (B5G) networks to intelligently learn and disseminate pandemic-related information and diagnostic results. However, such a technique raises privacy issues pertaining to the health data of the patients. In this paper, we envision a privacy-preserving pandemic response network using a proof-of-concept, aerial–terrestrial network system serving mobile user entities/equipment (UEs). By leveraging the unmanned aerial vehicles (UAVs), a lightweight federated learning model is proposed to collaboratively yet privately learn medical (e.g., COVID-19) symptoms with high accuracy using the data collected by individual UEs using ambient sensors and wearable devices. An asynchronous weight updating technique is introduced in federated learning to avoid redundant learning and save precious networking as well as computing resources of the UAVs/UEs. A use-case where an Artificial Intelligence (AI)-based model is employed for COVID-19 detection from radiograph images is presented to demonstrate the effectiveness of our proposed approach.

FedSPL: federated self-paced learning for privacy-preserving disease diagnosis.

The growing expansion of data availability in medical fields could help improve the performance of machine learning methods. However, with healthcare data, using multi-institutional datasets is challenging due to privacy and security concerns. Therefore, privacy-preserving machine learning methods are required. Thus, we use a federated learning model to train a shared global model, which is a central server that does not contain private data, and all clients maintain the sensitive data in their own institutions. The scattered training data are connected to improve model performance, while preserving data privacy. However, in the federated training procedure, data errors or noise can reduce learning performance. Therefore, we introduce the self-paced learning, which can effectively select high-confidence samples and drop high noisy samples to improve the performances of the training model and reduce the risk of data privacy leakage. We propose the federated self-paced learning (FedSPL), which combines the advantage of federated learning and self-paced learning. The proposed FedSPL model was evaluated on gene expression data distributed across different institutions where the privacy concerns must be considered. The results demonstrate that the proposed FedSPL model is secure, i.e. it does not expose the original record to other parties, and the computational overhead during training is acceptable. Compared with learning methods based on the local data of all parties, the proposed model can significantly improve the predicted F1-score by approximately 4.3%. We believe that the proposed method has the potential to benefit clinicians in gene selections and disease prognosis.

Pain-FL: Personalized Privacy-Preserving Incentive for Federated Learning

Federated learning (FL) is a privacy-preserving distributed machine learning framework, which involves training statistical models over a number of mobile users (i.e., workers) while keeping data localized. However, recent works have demonstrated that workers engaged in FL are still susceptible to advanced inference attacks when sharing model updates or gradients, which would discourage them from participating. Most of the existing incentive mechanisms for FL mainly account for workers’ resource cost, while the cost incurred by potential privacy leakage resulting from inference attacks has rarely been incorporated. To address these issues, in this paper, we propose a contract-based personalized privacy-preserving incentive for FL, named Pain-FL, to provide customized payments for workers with different privacy preferences as compensation for privacy leakage cost while ensuring satisfactory convergence performance of FL models. The core idea of Pain-FL is that each worker agrees on a customized contract, which specifies a kind of privacy-preserving level (PPL) and the corresponding payment, with the server in each round of FL. Then, the worker perturbs her calculated stochastic gradients to be uploaded with that PPL in exchange for that payment. In particular, we respectively derive a set of optimal contracts analytically under both complete and incomplete information models, which could optimize the convergence performance of the finally learned global model, while bearing some desired economic properties, i.e., budget feasibility, individual rationality, and incentive compatibility. An exhaustive experimental evaluation of Pain-FL is conducted, and the results corroborate its practicability and effectiveness.

Wireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems.

In this paper, the optimization of network performance to support the deployment of federated learning (FL) is investigated. In particular, in the considered model, each user owns a machine learning (ML) model by training through its own dataset, and then transmits its ML parameters to a base station (BS) which aggregates the ML parameters to obtain a global ML model and transmits it to each user. Due to limited radio frequency (RF) resources, the number of users that participate in FL is restricted. Meanwhile, each user uploading and downloading the FL parameters may increase communication costs thus reducing the number of participating users. To this end, we propose to introduce visible light communication (VLC) as a supplement to RF and use compression methods to reduce the resources needed to transmit FL parameters over wireless links so as to further improve the communication efficiency and simultaneously optimize wireless network through user selection and resource allocation. This user selection and bandwidth allocation problem is formulated as an optimization problem whose goal is to minimize the training loss of FL. We first use a model compression method to reduce the size of FL model parameters that are transmitted over wireless links. Then, the optimization problem is separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The ultimate user selection and bandwidth allocation are obtained by iteratively compressing the model and solving these two subproblems. Simulation results show that the proposed FL algorithm can improve the accuracy of object recognition by up to 16.7% and improve the number of selected users by up to 68.7%, compared to a conventional FL algorithm using only RF.

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data.

PurposeTo evaluate the performance of a federated learning framework for deep neural network-based retinal microvasculature segmentation and referable diabetic retinopathy (RDR) classification using OCT and OCT angiography (OCTA).DesignRetrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes.ParticipantsThe 153 OCTA en face images used for microvasculature segmentation were acquired from 4 OCT instruments with fields of view ranging from 2 × 2-mm to 6 × 6-mm. The 700 eyes used for RDR classification consisted of OCTA en face images and structural OCT projections acquired from 2 commercial OCT systems.MethodsOCT angiography images used for microvasculature segmentation were delineated manually and verified by retina experts. Diabetic retinopathy (DR) severity was evaluated by retinal specialists and was condensed into 2 classes: non-RDR and RDR. The federated learning configuration was demonstrated via simulation using 4 clients for microvasculature segmentation and was compared with other collaborative training methods. Subsequently, federated learning was applied over multiple institutions for RDR classification and was compared with models trained and tested on data from the same institution (internal models) and different institutions (external models).Main Outcome MeasuresFor microvasculature segmentation, we measured the accuracy and Dice similarity coefficient (DSC). For severity classification, we measured accuracy, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, balanced accuracy, F1 score, sensitivity, and specificity.ResultsFor both applications, federated learning achieved similar performance as internal models. Specifically, for microvasculature segmentation, the federated learning model achieved similar performance (mean DSC across all test sets, 0.793) as models trained on a fully centralized dataset (mean DSC, 0.807). For RDR classification, federated learning achieved a mean AUROC of 0.954 and 0.960; the internal models attained a mean AUROC of 0.956 and 0.973. Similar results are reflected in the other calculated evaluation metrics.ConclusionsFederated learning showed similar results to traditional deep learning in both applications of segmentation and classification, while maintaining data privacy. Evaluation metrics highlight the potential of collaborative learning for increasing domain diversity and the generalizability of models used for the classification of OCT data.

Fully Decentralized Federated Learning-Based On-Board Mission for UAV Swarm System

To handle the data explosion in the era of Internet-of-things, it is of interest to investigate the decentralized network, with the aim at relaxing the burden at the central server along with preserving data privacy. In this work, we develop a fully decentralized federated learning (FL) framework with an inexact stochastic parallel random walk alternating direction method of multipliers (ISPW-ADMM). Performing more efficient communication and enhanced privacy preservation compared with the current state-of-the-art, the proposed ISPW-ADMM can be partially immune to the effect of time-varying dynamic network and stochastic data collection, while still in fast convergence. Benefiting from the stochastic gradients and biased first-order moment estimation, the proposed framework can be applied to any decentralized FL tasks over time-varying graphs. Thus, to demonstrate the practicability of such a framework in providing fast convergence, high communication efficiency, noise robustness for a specific on-board mission to some extent, we study the extreme learning machine-based FL model beamforming design in unmanned aerial vehicle communications, as verified by the numerical simulations.

Federated Learning and Wireless Communications

Federated learning becomes increasingly attractive in the areas of wireless communications and machine learning due to its powerful learning ability and potential applications. In contrast to other machine learning techniques that require no communication resources, federated learning exploits communications between the central server and the distributed local clients to train and optimize a model. Therefore, how to efficiently assign limited communication resources to train a federated learning model becomes critical to performance optimization. On the other hand, federated learning, as a brand-new tool, can potentially enhance the intelligence of wireless networks. In this article, we provide a comprehensive overview of the relationship between federated learning and wireless communications, including basic principles of federated learning, efficient communications for training a federated learning model, and federated learning for intelligent wireless applications. We also identify some research challenges and directions at the end of this article.