Aggregation Algorithm Research Articles

DP-Poison: Poisoning Federated Learning under the Cover of Differential Privacy

Federated learning (FL) enables resource-constrained node devices to learn a shared model while keeping the training data local. Since recent research has demonstrated multiple privacy leakage attacks in FL, e.g., gradient inference attacks and membership inference attacks, differential privacy (DP) is applied to serve as one of the most effective privacy protection mechanisms. Despite the benefit DP brings, we observe that the introduction of DP also brings random changes to client updates, which will affect the robust aggregation algorithms. We reveal a novel poisoning attack under the cover of DP, named the DP-Poison attack in FL. Specifically, the DP-Poison attack is designed to achieve four goals: 1) maintaining the main task performance; 2) launching a successful attack; 3) escaping the robust aggregation algorithms in FL; and 4) keeping the effectiveness of DP privacy protection. To achieve these goals, we design multiple optimization goals to generate DP noise through a genetic algorithm. The optimization ensures that while the benign updates change randomly, the malicious updates can change towards the global model after adding the DP noise, so that it is easier to be accepted by the robust aggregation algorithms. Extensive experiments show that DP-Poison achieves a nearly 100% attack success rate while maintaining the proposed four goals.

Surrogate modeling of multi-dimensional premixed and non-premixed combustion using pseudo-time stepping physics-informed neural networks

Physics-informed neural networks (PINNs) have emerged as a promising alternative to conventional computational fluid dynamics (CFD) approaches for solving and modeling multi-dimensional flow fields. They offer instant inference speed and cost-effectiveness without the need for training datasets. However, compared to common data-driven methods, purely learning the physical constraints of partial differential equations and boundary conditions is much more challenging and prone to convergence issues leading to incorrect local optima. This training robustness issue significantly increases the difficulty of fine-tuning PINNs and limits their widespread adoption. In this work, we present improvements to the prior field-resolving surrogate modeling framework for combustion systems based on PINNs. First, inspired by the time-stepping schemes used in CFD numerical methods, we introduce a pseudo-time stepping loss aggregation algorithm to enhance the convergence robustness of the PINNs training process. This new pseudo-time stepping PINNs (PTS-PINNs) method is then tested in non-reactive convection–diffusion problem, and the results demonstrated its good convergence capability for multi-species transport problems. Second, the effectiveness of the PTS-PINNs method was verified in the case of methane–air premixed combustion, and the results show that the L2 norm relative error of all variables can be reduced within 5%. Finally, we also extend the capability of the PTS-PINNs method to address a more complex methane–air non-premixed combustion problem. The results indicate that the PTS-PINNs method can still achieve commendable accuracy by reducing the relative error to within 10%. Overall, the PTS-PINNs method demonstrates the ability to rapidly and accurately identify the convergence direction of the model, surpassing traditional PINNs methods in this regard.

Heterogeneous graph neural network for modeling intelligent manufacturing systems

Abstract Currently, manufacturing systems have become more and more complex, often involving multiple machines, systems and processes to produce workpieces. In order to facilitate comprehensive analysis and control of manufacturing processes, the integration of connections between machine level, system level, and process level in manufacturing process modeling is needed. However, traditional graph deep learning models are unable to take into account the heterogeneity of different machines in the system when modeling manufacturing systems. To address this problem, this paper proposes a new approach: modeling manufacturing systems using the heterogeneous graph neural network sample and aggregate algorithm based on cutting-edge Bayesian neural networks and graph deep learning. This method considers the connection between different manufacturing system levels, treats machine operations as nodes, and connects different nodes through material flow and operational similarity. The effectiveness of the method is demonstrated through its application to model an aero-engine blade production line. Extensive numerical experiments show that the proposed graph modeling method is effective in expressing the heterogeneity of different machines and multi-level manufacturing processes. By integrating machine heterogeneity into the modeling of a manufacturing system, it not only facilitates comprehensive analysis and control of the manufacturing process, but also lays the foundation for cost savings and productivity improvements in the manufacturing system.

Does the FARNet neural network algorithm accurately identify Posteroanterior cephalometric landmarks?

BackgroundWe explored whether the feature aggregation and refinement network (FARNet) algorithm accurately identified posteroanterior (PA) cephalometric landmarks.MethodsWe identified 47 landmarks on 1,431 PA cephalograms of which 1,177 were used for training, 117 for validation, and 137 for testing. A FARNet-based artificial intelligence (AI) algorithm automatically detected the landmarks. Model effectiveness was calculated by deriving the mean radial error (MRE) and the successful detection rates (SDRs) within 2, 2.5, 3, and 4 mm. The Mann-Whitney U test was performed on the Euclidean differences between repeated manual identifications and AI trials. The direction in differences was analyzed, and whether differences moved in the same or opposite directions relative to ground truth on both the x and y-axis.ResultsThe AI system (web-based CranioCatch annotation software (Eskişehir, Turkey)) identified 47 anatomical landmarks in PA cephalograms. The right gonion SDRs were the highest, thus 96.4, 97.8, 100, and 100% within 2, 2.5, 3, and 4 mm, respectively. The right gonion MRE was 0.94 ± 0.53 mm. The right condylon SDRs were the lowest, thus 32.8, 45.3, 54.0, and 67.9% within the same thresholds. The right condylon MRE was 3.31 ± 2.25 mm. The AI model’s reliability and accuracy were similar to a human expert’s. AI was better at four skeleton points than the expert, whereas the expert was better at one skeletal and seven dental points (P < 0.05). Most of the points exhibited significant deviations along the y-axis. Compared to ground truth, most of the points in AI and the second trial showed opposite movement on the x-axis and the same on the y-axis.ConclusionsThe FARNet algorithm streamlined orthodontic diagnosis.

Enhancing federated learning with dynamic weight adjustment based on particle swarm optimization

Federated learning (FL) stands as a promising distributed machine learning approach today, allowing model training on local clients without data sharing. However, varied contributions among clients often impact the global model’s performance, while FL confronts challenges like communication overhead, data heterogeneity, and privacy concerns. In this paper, we introduce a novel federated learning server aggregation algorithm: the Federated Learning Algorithm with Optimized Weight Aggregation via Particle Swarm Optimization Algorithm (AdpFedPSO). This approach dynamically adjusts client model contribution weights based on their performance and stability, aiming to enhance global model accuracy, convergence speed, and make model aggregation smarter and more adaptable. Through experimental validation on real datasets, we find that AdpFedPSO enhances accuracy by about 15% on the 0.6-Dirichlet MNIST dataset, 7.3% on the FashionMNIST dataset, and 13.4% on the CIFAR-10 dataset compared to the traditional FL aggregation method, FedAvg. These results indicate that AdpFedPSO not only enhances the accuracy of the global model but also expedites the model’s convergence speed. Additionally, it demonstrates resilience across various levels of client numbers, participation rates, and client heterogeneity, providing valuable reference and guidance for the further development of FL technology. Moreover, the concept of employing the particle swarm optimization algorithm for FL model aggregation also offers new insights and directions for future research.

Efficient and secure service function chain deployment method for delay optimization in air traffic information network

The air traffic information network is fundamental for ensuring the efficient and safe operation of flights. However, with the increasing demands of air traffic services, the rigidity of the traditional air traffic information network has become increasingly pronounced. Network function virtualization (NFV) technology presents an effective solution to address this issue. Within the NFV environment, the deployment of service function chains (SFC) forms the basis for achieving end-to-end air traffic services. This paper addresses the low delay and high security requirements inherent in air traffic services and proposes an efficient and secure SFC deployment for delay optimization (ESSFCD-DO) method. Primarily, the paper conducts a theoretical analysis of SFC deployment, and derives four key principles related to SFC delay, security, and resource cost. Subsequently, based on these principles, the ESSFCD-DO method is developed, which encompasses the virtual network function (VNF) aggregation algorithm for security and resources cost optimization (VNFAA-SRCO), the VNF deployment algorithm based on topology aware (VNFD-TA), and the algorithm for deploying virtual links based on k-shortest path. Experimental results demonstrate that, in comparison to other SFC deployment methods within this domain, ESSFCD-DO achieves significant optimizations in terms of end-to-end delay of SFC and long-term revenue-cost ratio, while ensuring security and service request acceptance rate.

SERPINH1 as a Novel Biomarker for Colon Cancer Bone Metastasis with Machine Learning and Immunohistochemistry Validation.

Background: Bone metastasis (BM) is a serious clinical symptom of advanced colorectal cancer. However, there is a lack of effective biomarkers for early diagnosis and treatment. Method: RNA-seq data from public databases (GSE49355, GSE101607) were collected and normalized and batch effects were removed using the combat package. Differential expression analysis was performed to identify significant genes. Robust Rank Aggregation and machine learning algorithms were used to pinpoint candidate biomarkers. These biomarkers were validated using immunohistochemistry and further analyzed for survival rates. Enrichment analysis was conducted to explore biological mechanisms. Additionally, drug sensitivity and immune infiltration analyses were performed to provide insights into potential therapeutic targets. Results: Analysis results revealed 386 genes elevated in primary versus normal tissues and 26 genes varying between primary and BM. Serpin Protease Inhibitor Clade H1 (SERPINH1) as a novel biomarker for colon cancer metastasis. High SERPINH1 expression correlates with poor survival outcomes and is linked to high lymphatic invasion and advanced cancer stages. Additionally, SERPINH1 expression influences immune infiltration and is not predictive of chemotherapy response, but potential new drugs are suggested for high-expression cases. The gene also enriches classical cancer pathways such as Hedgehog and transforming growth factor-β. Conclusions: We identified novel colon cancer BM markers, including SERPINH1, using machine learning algorithms combined with traditional transcriptomic data and validated their expression through immunohistochemistry. This biomarker could significantly assist clinicians in making more precise treatment decisions.

Modelling the temporal-varied nonlinear velocity profile of debris flow using a stratification aggregation algorithm in 3D-HBP-SPH framework

Modelling the temporal-varied nonlinear velocity profile of debris flow using a stratification aggregation algorithm in 3D-HBP-SPH framework

Decentralized collaborative machine learning for protecting electricity data

In recent years, there has been a noticeable surge in electric power load due to economic development and improved living standards. The growing need for smart power solutions, such as leveraging user electricity data to forecast power peaks and utilizing power data statistics to enhance end-user services, has been on the rise. However, the misuse and unauthorized access of data have prompted stringent regulations to safeguard data integrity. This paper presents a novel decentralized collaborative machine learning framework aimed at predicting peak power loads while protecting the privacy of users’ power data. In this scheme, multiple users engage in collaborative machine learning training within a peer-to-peer network free from a centralized server, with the objective of predicting peak power loads without compromising users’ local data privacy. The proposed approach leverages blockchain technology and advanced cryptographic techniques, including multi-key homomorphic encryption and consistent hashing. Key contributions of this framework include the development of a secure dual-aggregate node aggregation algorithm and the establishment of a verifiable process within a decentralized architecture. Experimental validation has been conducted to assess the feasibility and effectiveness of the proposed scheme, demonstrating its potential to address the challenges associated with predicting peak power loads securely and preserving user data privacy.

BRFL: A blockchain-based byzantine-robust federated learning model

With the increasing importance of machine learning, the privacy and security of training data have become a concern. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant attention for addressing this concern. However, a challenge arises in federated learning due to the byzantine attack problem, where malicious local models can compromise the global model's performance during aggregation. This article proposes the Blockchain-based Byzantine-Robust Federated Learning (BRFL) model, which combines federated learning with blockchain technology. We improve the robustness of federated learning by proposing a new consensus algorithm and aggregation algorithm for blockchain-based federated learning. Meanwhile, we modify the block saving rules of the blockchain to reduce the storage pressure of the nodes. Experimental results on public datasets demonstrate the superior byzantine robustness of our secure aggregation algorithm compared to other baseline aggregation methods, and reduce the storage pressure of the blockchain nodes.

Edge-assisted U-shaped split federated learning with privacy-preserving for Internet of Things

In the realm of the Internet of Things (IoT), deploying deep learning models to process data generated or collected by IoT devices is a critical challenge. However, direct data transmission can cause network congestion and inefficient execution, given that IoT devices typically lack computation and communication capabilities. Centralized data processing in data centers is also no longer feasible due to concerns over data privacy and security. To address these challenges, we present an innovative Edge-assisted U-Shaped Split Federated Learning (EUSFL) framework, which harnesses the high-performance capabilities of edge servers to assist IoT devices in model training and optimization process. In this framework, we leverage Federated Learning (FL) to enable data holders to collaboratively train models without sharing their data, thereby enhancing data privacy protection by transmitting only model parameters. Additionally, inspired by Split Learning (SL), we split the neural network into three parts using U-shaped splitting for local training on IoT devices. By exploiting the greater computation capability of edge servers, our framework effectively reduces overall training time and allows IoT devices with varying capabilities to perform training tasks efficiently. Furthermore, we proposed a novel noise mechanism called LabelDP to ensure that data features and labels can securely resist reconstruction attacks, eliminating the risk of privacy leakage. Our theoretical analysis and experimental results demonstrate that EUSFL can be integrated with various aggregation algorithms, maintaining good performance across different computing capabilities of IoT devices, and significantly reducing training time and local computation overhead.

Simulation of Dendrite Growth with a Diffusion-Limited Aggregation Model Validated by MRI of a Lithium Symmetric Cell during Charging

Lithium metal batteries offer high energy density but are challenged by dendrite growth, which can lead to short circuits and battery failure. Multiple models with varying degrees of accuracy and computational cost have been developed to understand and predict dendrite growth. This study presents a simple model to simulate macroscale dendrite growth on lithium metal electrodes. The model uses a 3D single-particle Diffusion-Limited Aggregation (DLA) algorithm with an electric field bias to simulate dendrite growth. The electric field bias was introduced into the model with an important parameter, namely the biasing factor c, which determines the balance between diffusion and electric field effects. Before performing the simulation with the proposed model, the dendrite growth in a lithium symmetric cell during charging was measured by sequential 3D magnetic resonance imaging (MRI). These data were then used to validate the simulation, as the dendrite structure in each measured MRI time frame was used a starting point for a new simulation, the results of which were then validated with the measured dendrite structure of the next time frame. The best agreement between the simulated and measured dendrite structures using the overlap and displacement of deposition sites metrics was obtained at the biasing factor c = 0.7. This agreement was also good in terms with the fractal dimension of the dendrite structures. The proposed method offers a simple, accurate, and scalable framework for predicting dendrite growth over long deposition periods, making it a valuable tool for studying dendrite suppression under real-world battery charging conditions.

A robust federated learning algorithm for partially trusted environments

Due to the distributed nature of federated learning, it is vulnerable to poisoning attacks during the training process. The model’s resistance to poisoning attacks can be improved using robust aggregation algorithms. Current research on federated learning to resist poisoning attacks is mainly based on two settings: No trust or Byzantine robustness. However, both settings are not close enough to reality in practical scenarios. In many practical applications, some participants in federated learning are trustworthy. For example, participants who have participated in the training of this model before and performed very well, or participants with strong compliance and credibility such as governments and some national agencies participate in the training. In existing research, these trusted participants still have to accept the judgment of the aggregation node, which generates unnecessary computation, increases overhead, and does not take advantage of a trusted environment. Since there is no attack behavior on the trusted client, its training results are used to classify the trustworthiness of other untrusted clients and identify attack nodes with higher accuracy. Therefore, this paper proposes a robust federated learning algorithm for partially trusted environments. The proposed scheme uses the experimental results of trusted clients to judge the behavior of untrustworthy clients by the cosine similarity and the Local Outlier Factor and further identify and detect malicious clients. Experiments are performed on MNIST and CIFAR datasets. Comparison with other six aggregation algorithms under 30% attack scenario. And compared with the other four aggregation algorithms under 70% attack conditions. Our algorithm is more accurate than almost all of the other aggregation algorithms. The paper is the first to conduct robust research on federated learning in a partially trusted environment, and the proposed algorithm can more effectively resist poisoning attacks.

Computational Design with Kurtboğaz: The Generation of Timber Structures with an Aggregative Design Algorithm

This paper investigates the form-finding capacity of the traditional timber-joint construction method, Kurtboğaz, aiming to explore new architectural forms and possibilities through computational design techniques to preserve vernacular construction methods and integrate them into contemporary architecture. It presents an Aggregative Design Algorithm (ADA) that creates different structures based on designer rules and simple assembly rules of Kurtboğaz, leading to unique emergent forms through random rule application. The paper also explores how reinforcement learning, a type of machine learning, can improve this design process through a theoretical framework. The study tries to use a rule-based generative algorithm to explore the modular and reconfigurable characteristics of the Kurtboğaz. The ADA enables random rule application, leading to diverse forms. However, several challenges may be encountered during the application of ADA because of its random aggregation, such as collision avoidance, structural integrity, boundary detection, and the optimization of structural parameters. The study suggests using Reinforcement Learning (RL) in the ADA framework to address these problems. Incorporating RL is anticipated to enable the algorithm to adaptively learn and optimize the form-finding process, enhancing the performance and applicability of the Kurtboğaz method in contemporary architectural practice. In the future, with this generative process described by the study, designs that create spatial differences with the help of walls, floors, and rooms on a human scale can be realized. The study also plans to explore the synergy between craftsmanship and digital fabrication in the future

HoLens: A visual analytics design for higher-order movement modeling and visualization

Higher-order patterns reveal sequential multistep state transitions, which are usually superior to origin-destination analyses that depict only firstorder geospatial movement patterns. Conventional methods for higher-order movement modeling first construct a directed acyclic graph (DAG) of movements and then extract higher-order patterns from the DAG. However, DAG-based methods rely heavily on identifying movement keypoints, which are challenging for sparse movements and fail to consider the temporal variants critical for movements in urban environments. To overcome these limitations, we propose HoLens, a novel approach for modeling and visualizing higher-order movement patterns in the context of an urban environment. HoLens mainly makes twofold contributions: First, we designed an auto-adaptive movement aggregation algorithm that self-organizes movements hierarchically by considering spatial proximity, contextual information, and temporal variability. Second, we developed an interactive visual analytics interface comprising well-established visualization techniques, including the H-Flow for visualizing the higher-order patterns on the map and the higher-order state sequence chart for representing the higher-order state transitions. Two real-world case studies demonstrate that the method can adaptively aggregate data and exhibit the process of exploring higher-order patterns using HoLens. We also demonstrate the feasibility, usability, and effectiveness of our approach through expert interviews with three domain experts.

Controlling the False Split Rate in Tree-Based Aggregation

In many domains, data measurements can naturally be associated with the leaves of a tree, expressing the relationships among these measurements. For example, companies belong to industries, which in turn belong to ever coarser divisions such as sectors; microbes are commonly arranged in a taxonomic hierarchy from species to kingdoms; street blocks belong to neighborhoods, which in turn belong to larger-scale regions. The problem of tree-based aggregation that we consider in this article asks which of these tree-defined subgroups of leaves should really be treated as a single entity and which of these entities should be distinguished from each other. We introduce the false split rate, an error measure that describes the degree to which subgroups have been split when they should not have been. While expressible as the false discovery rate in a special case, we show that these measures can be quite different for the general tree structures common in our setting. We then propose a multiple hypothesis testing algorithm for tree-based aggregation, which we prove controls this error measure. We focus on two main examples of tree-based aggregation, one which involves aggregating means and the other hich involves aggregating regression coefficients. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Survey of federated learning in intrusion detection

Intrusion detection methods are crucial means to mitigate network security issues. However, the challenges posed by large-scale complex network environments include local information islands, regional privacy leaks, communication burdens, difficulties in handling heterogeneous data, and storage resource bottlenecks. Federated learning has the potential to address these challenges by leveraging widely distributed and heterogeneous data, achieving load balancing of storage and computing resources across multiple nodes, and reducing the risks of privacy leaks and bandwidth resource demands. This paper reviews the process of constructing federated learning based intrusion detection system from the perspective of intrusion detection. Specifically, it outlines six main aspects: application scenario analysis, federated learning methods, privacy and security protection, selection of classification models, data sources and client data distribution, and evaluation metrics, establishing them as key research content. Subsequently, six research topics are extracted based on these aspects. These topics include expanding application scenarios, enhancing aggregation algorithm, enhancing security, enhancing classification models, personalizing model and utilizing unlabeled data. Furthermore, the paper delves into research content related to each of these topics through in-depth investigation and analysis. Finally, the paper discusses the current challenges faced by research, and suggests promising directions for future exploration.

HPNet: Text Detection Network with Hybrid Attention and Pixel Aggregation for Irregularly-Shaped Nearby Texts

Scene text detection is a challenging topic in computer vision, characterized by complex illumination, irregular shape, and arbitrary size. While recent advancements have been made in scene text detection, it remains difficult to simultaneously distinguish nearby text and accommodate irregularly shaped text. Therefore, this paper introduces HPNet, an enhanced text detector, based on the segmentation method that predicts two-scale results. To improve the shape robustness, the Hybrid Attentional Feature Fusion (HAFF) module is integrated into Feature Pyramid Networks (FPN) to dynamically perform feature fusion. Additionally, to distinguish nearby text, the model predicts the text region covering text instances and the text kernel covering the central region of the text. The improved Pixel Aggregation (PA) algorithm is then utilized to guide the expansion from the text kernel to the text region. Experiments on IC15, Total-Text, and CTW1500 validate the effectiveness of these improvements and the superiority of HPNet. Compared with the previous method PSENet for nearby texts, the proposed HPNet has improved inference speed by 63.6% and F-measure metric by 2.6%, 3.7%, and 2.5% on three datasets, respectively.

Mobility-aware federated self-supervised learning in vehicular network

The development of the Internet of Things has led to a significant increase in the number of devices, consequently generating a vast amount of data and resulting in an influx of unlabeled data. Collecting these data enables the training of robust models to support a broader range of applications. However, labeling these data can be costly, and the models dependent on labeled data are often unsuitable for rapidly evolving fields like vehicular networks and mobile Internet of Things, where new data continuously emerge. To address this challenge, Self-Supervised Learning (SSL) offers a way to train models without the need for labels. Nevertheless, the data stored locally in vehicles are considered private, and vehicles are reluctant to share data with others. Federated Learning (FL) is an advanced distributed machine learning approach that protects each vehicle’s privacy by allowing models to be trained locally and the model parameters to be exchanged across multiple devices simultaneously. Additionally, vehicles capture images while driving through cameras mounted on their rooftops. If a vehicle’s velocity is too high, the captured images, donated as local data, may be blurred. Simple aggregation of such data can negatively impact the accuracy of the aggregated model and slow down the convergence speed of FL. This paper proposes a FL algorithm for aggregation based on image blur levels, which is called FLSimCo. This algorithm does not require labels and serves as a pre-training stage for SSL in vehicular networks. Simulation results demonstrate that the proposed algorithm achieves fast and stable convergence.

Forage Height and Above-Ground Biomass Estimation by Comparing UAV-Based Multispectral and RGB Imagery.

Crop height and biomass are the two important phenotyping traits to screen forage population types at local and regional scales. This study aims to compare the performances of multispectral and RGB sensors onboard drones for quantitative retrievals of forage crop height and biomass at very high resolution. We acquired the unmanned aerial vehicle (UAV) multispectral images (MSIs) at 1.67 cm spatial resolution and visible data (RGB) at 0.31 cm resolution and measured the forage height and above-ground biomass over the alfalfa (Medicago sativa L.) breeding trials in the Canadian Prairies. (1) For height estimation, the digital surface model (DSM) and digital terrain model (DTM) were extracted from MSI and RGB data, respectively. As the resolution of the DTM is five times less than that of the DSM, we applied an aggregation algorithm to the DSM to constrain the same spatial resolution between DSM and DTM. The difference between DSM and DTM was computed as the canopy height model (CHM), which was at 8.35 cm and 1.55 cm for MSI and RGB data, respectively. (2) For biomass estimation, the normalized difference vegetation index (NDVI) from MSI data and excess green (ExG) index from RGB data were analyzed and regressed in terms of ground measurements, leading to empirical models. The results indicate better performance of MSI for above-ground biomass (AGB) retrievals at 1.67 cm resolution and better performance of RGB data for canopy height retrievals at 1.55 cm. Although the retrieved height was well correlated with the ground measurements, a significant underestimation was observed. Thus, we developed a bias correction function to match the retrieval with the ground measurements. This study provides insight into the optimal selection of sensor for specific targeted vegetation growth traits in a forage crop.