Label Propagation Method Research Articles

Few-shot Learning for Sign Language Recognition with Embedding Propagation

Sign language is a primary channel for the deaf and hard-hearing to communicate. Sign language consists of many signs with different variations in hand shapes, motion patterns, and positioning of hands, faces, and body parts. This makes sign language recognition (SLR) a challenging field in computer vision research. This paper tackles the problem of few-shot SLR, where models trained on known sign classes are utilized to recognize instances of unseen signs with only a few examples. In this approach, a transformer encoder is employed to learn the spatial and temporal features of sign gestures, and an embedding propagation technique is used to project these features into the embedding space. Subsequently, a label propagation method is applied to smooth the resulting embeddings. The obtained results demonstrate that combining embedding propagation with label propagation enhances the performance of the SLR system and achieved an accuracy of 76.6%, which surpasses the traditional few-shot prototypical network's accuracy of 72.4%.

Predicting Microbe-Disease Associations Based on a Linear Neighborhood Label Propagation Method with Multi-order Similarity Fusion Learning.

Computational approaches employed for predicting potential microbe-disease associations often rely on similarity information between microbes and diseases. Therefore, it is important to obtain reliable similarity information by integrating multiple types of similarity information. However, existing similarity fusion methods do not consider multi-order fusion of similarity networks. To address this problem, a novel method of linear neighborhood label propagation with multi-order similarity fusion learning (MOSFL-LNP) is proposed to predict potential microbe-disease associations. Multi-order fusion learning comprises two parts: low-order global learning and high-order feature learning. Low-order global learning is used to obtain common latent features from multiple similarity sources. High-order feature learning relies on the interactions between neighboring nodes to identify high-order similarities and learn deeper interactive network structures. Coefficients are assigned to different high-order feature learning modules to balance the similarities learned from different orders and enhance the robustness of the fusion network. Overall, by combining low-order global learning with high-order feature learning, multi-order fusion learning can capture both the shared and unique features of different similarity networks, leading to more accurate predictions of microbe-disease associations. In comparison to six other advanced methods, MOSFL-LNP exhibits superior prediction performance in the leave-one-out cross-validation and 5-fold validation frameworks. In the case study, the predicted 10 microbes associated with asthma and type 1 diabetes have an accuracy rate of up to 90% and 100%, respectively.

Enhancing Semi Supervised Semantic Segmentation Through Cycle-Consistent Label Propagation in Video

To perform semantic image segmentation using deep learning models, a significant quantity of data and meticulous manual annotation is necessary (Mani in: Research anthology on improving medical imaging techniques for analysis and intervention. IGI Global, pp. 107–125, 2023), and the process consumes a lot of resources, including time and money. To resolve such issues, we introduce a unique label propagation method (Qin et al. in IEEE/CAA J Autom Sinica 10(5):1192–1208, 2023) that utilizes cycle consistency across time to propagate labels over longer time horizons with higher accuracy. Additionally, we acknowledge that dense pixel annotation is a noisy process (Das et al. in: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp. 5978–5987, 2023), whether performed manually or automatically. To address this, we present a principled approach that accounts for label uncertainty when training with labels from multiple noisy labeling processes. We introduce two new approaches; Warp-Refine Propagation and Uncertainty-Aware Training, for improving label propagation and handling noisy labels, respectively, and support the process with quantitative and qualitative evaluations and theoretical justification. Our contributions are validated on the Cityscapes and ApolloScape datasets, where we achieve encouraging results. In later endeavors, the aim should be to expand such approaches to include other noisy augmentation processes like image-based rendering methods (Laraqui et al. in Int J Comput Aid Eng Technol 18(5):141–151, 2023), thanks to the noisy label learning approach.

Exploring the Status Quo and Teaching Mode of College English Education in the Information Age

Abstract With the rapid development of the information age, new technological means are constantly applied to the field of education and produce good results. This paper uses data mining algorithms to extract and analyze data on college English education and explore how to adjust the teaching methodology. On the basis of improving the inherent defects of the DPC algorithm, this paper determines the clustering center through a scoring function, uses the K-neighbor method to form the cluster backbone, and proposes a nearest-neighbor-based label propagation method to propagate the labels to their adjacent nodes to complete data mining. After mining and analyzing the current situation of English education, it was found that the age group over 30 years old accounted for 77.6%, female teachers accounted for 74.6% of the total number of teachers, teachers with the titles of lecturer and assistant professor accounted for 58%, and 33% of the students were not too satisfied or dissatisfied with the content of the English course. It shows that the English teaching team of universities in this province has shortcomings such as gender imbalance, insufficient young and senior teachers, and less than satisfactory content of English courses, which need to be improved in several aspects.

An information‐sharing framework of patient label propagation method to reveal distinct blood biomarkers and signatures in Alzheimer’s disease subgroups

AbstractBackgroundAlzheimer’s Disease (AD) is a complex and heterogenous dementia and the early detection remains very challenging. Although progresses have been made to identify serum biomarkers associated with AD, it is still difficult to generalize the findings into clinical setting and trace back to learn how these AD biomarkers are progressed through the regulatory pathways and how they play the roles in the disease mechanisms. Furthermore, distinct patterns or signatures among atypical progressing subgroups has not been investigated.MethodWe defined four subgroups of AD patients based on the trajectories of tauopathy and cognitive decline. Using the blood transcriptomic data from ROSMAP and ADNI, we performed hierarchical clustering for the top 1000 variable genes to obtain the gene signatures in each group. An NMF‐based decomposition and network assisted label propagation method was applied. Finally, we use the inferred label for ADNI patients to assess the distinct progression patterns for each AD subtype and validate and uncovering the genes and their enriched pathways that are associated with flagged progression biomarkers.ResultOur preliminary results show that two gene expression clusters exist for both ROSMAP and ADNI data. Our previous study identified the activation of calcium channel related pathway exhibits a detrimental role in AD, with representative genes such as TGFB1, and S100A12. We observe the same pattern for these two genes in a subset of patients from ADNI gene expression data with an enrichment in neovascularization processes. We are now propagating patient group labels with the prior evidence of the alignment between these two data sets and investigating the primary genes linked to specific biomarker progression patterns through longitudinal analyses.ConclusionWe identified several altered pathways and genes that potentially render atypical AD progression patterns reflected by various biomarkers. Future work is undergoing to further explore the link between the gene signatures in each subgroup and the blood transcriptomic sub‐clusters, as well as the comparisons of the two blood transcriptomic data for potential longitudinal clinical information mapping between the two datasets.

Label Efficient Regularization and Propagation for Graph Node Classification.

An enhanced label propagation (LP) method called GraphHop was proposed recently. It outperforms graph convolutional networks (GCNs) in the semi-supervised node classification task on various networks. Although the performance of GraphHop was explained intuitively with joint node attribute and label signal smoothening, its rigorous mathematical treatment is lacking. In this paper, we propose a label efficient regularization and propagation (LERP) framework for graph node classification, and present an alternate optimization procedure for its solution. Furthermore, we show that GraphHop only offers an approximate solution to this framework and has two drawbacks. First, it includes all nodes in the classifier training without taking the reliability of pseudo-labeled nodes into account in the label update step. Second, it provides a rough approximation to the optimum of a subproblem in the label aggregation step. Based on the LERP framework, we propose a new method, named the LERP method, to solve these two shortcomings. LERP determines reliable pseudo-labels adaptively during the alternate optimization and provides a better approximation to the optimum with computational efficiency. Theoretical convergence of LERP is guaranteed. Extensive experiments are conducted to demonstrate the effectiveness and efficiency of LERP. That is, LERP outperforms all benchmarking methods, including GraphHop, consistently on five common test datasets, two large-scale networks, and an object recognition task at extremely low label rates (i.e., 1, 2, 4, 8, 16, and 20 labeled samples per class).

GraphHop: An Enhanced Label Propagation Method for Node Classification.

A scalable semisupervised node classification method on graph-structured data, called GraphHop, is proposed in this work. The graph contains all nodes' attributes and link connections but labels of only a subset of nodes. Graph convolutional networks (GCNs) have provided superior performance in node label classification over the traditional label propagation (LP) methods for this problem. Nevertheless, current GCN algorithms suffer from a considerable amount of labels for training because of high model complexity or cannot be easily generalized to large-scale graphs due to the expensive cost of loading the entire graph and node embeddings. Besides, nonlinearity makes the optimization process a mystery. To this end, an enhanced LP method, called GraphHop, is proposed to tackle these problems. GraphHop can be viewed as a smoothening LP algorithm, in which each propagation alternates between two steps: label aggregation and label update. In the label aggregation step, multihop neighbor embeddings are aggregated to the center node. In the label update step, new embeddings are learned and predicted for each node based on aggregated results from the previous step. The two-step iteration improves the graph signal smoothening capacity. Furthermore, to encode attributes, links, and labels on graphs effectively under one framework, we adopt a two-stage training process, i.e., the initialization stage and the iteration stage. Thus, the smooth attribute information extracted from the initialization stage is consistently imposed in the propagation process in the iteration stage. Experimental results show that GraphHop outperforms state-of-the-art graph learning methods on a wide range of tasks in graphs of various sizes (e.g., multilabel and multiclass classification on citation networks, social graphs, and commodity consumption graphs).

Incremental label propagation for data sets with imbalanced labels

Label Propagation (LP) is a popular graph-based semi-supervised learning algorithm. However, the imbalanced label distribution of labeled data affects the performance of LP, which makes it prefer to allocate more points for the class with majority labels. To get rid of this deficiency, we propose an Incremental Label Propagation (ILP) framework. The ILP framework includes an incremental balance strategy and a multiple results integration method to reduce the uncertainty of balancing labeled data. The incremental balance strategy can gradually add trusted pseudo labels to balance the label distribution so as to reduce the uncertainty caused by pseudo labels. Then, the integration method evaluates the quality of the balanced propagation results obtained from the incremental balance strategy and combines them with different weights to generate a robust outcome. The experimental results show that the proposed framework can combine with different LP methods and effectively solve the performance degradation of the LP algorithm caused by imbalanced labels.

Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm

Introduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully accessible datasets and open-source algorithms is slowing the improvements in this field. In this paper, we focus on the fully automatic segmentation of the Inferior Alveolar Canal (IAC), which is of immense interest in the dental and maxillo-facial surgeries. Conventionally, only a bidimensional annotation of the IAC is used in common clinical practice. A reliable convolutional neural network (CNNs) might be timesaving in daily practice and improve the quality of assistance. Materials and methods: Cone Beam Computed Tomography (CBCT) volumes obtained from a single radiological center using the same machine were gathered and annotated. The course of the IAC was annotated on the CBCT volumes. A secondary dataset with sparse annotations and a primary dataset with both dense and sparse annotations were generated. Three separate experiments were conducted in order to evaluate the CNN. The IoU and Dice scores of every experiment were recorded as the primary endpoint, while the time needed to achieve the annotation was assessed as the secondary end-point. Results: A total of 347 CBCT volumes were collected, then divided into primary and secondary datasets. Among the three experiments, an IoU score of 0.64 and a Dice score of 0.79 were obtained thanks to the pre-training of the CNN on the secondary dataset and the creation of a novel deep label propagation model, followed by proper training on the primary dataset. To the best of our knowledge, these results are the best ever published in the segmentation of the IAC. The datasets is publicly available and algorithm is published as open-source software. On average, the CNN could produce a 3D annotation of the IAC in 6.33 s, compared to 87.3 s needed by the radiology technician to produce a bidimensional annotation. Conclusions: To resume, the following achievements have been reached. A new state of the art in terms of Dice score was achieved, overcoming the threshold commonly considered of 0.75 for the use in clinical practice. The CNN could fully automatically produce accurate three-dimensional segmentation of the IAC in a rapid setting, compared to the bidimensional annotations commonly used in the clinical practice and generated in a time-consuming manner. We introduced our innovative deep label propagation method to optimize the performance of the CNN in the segmentation of the IAC. For the first time in this field, the datasets and the source codes used were publicly released, granting reproducibility of the experiments and helping in the improvement of IAC segmentation.

Signal Abstraction for Root Cause Identification of Control Systems Malfunctions in Connected Vehicles

Today’s automotive control systems have gained huge advantage from using integrated software and hardware to reliably manage the performance of vehicles. The integration of largescale software with many hardware components, however, have increased the complexity of diagnosis and root cause analysis for a detected malfunction. High level of expertise and detailed knowledge of the underlying software and hardware are typically required to analyze a large list of variables and precisely identify the root cause of the malfunction. In this paper, an abstraction method is presented to identify the most important signals for a root cause analysis by leveraging data collected from a connected fleet of field vehicles. A novel label propagation methodology is proposed to select the most relevant signals for the root cause analysis by detecting linear and nonlinear correlations between an observed malfunction and candidate test signals of the control system. The proposed label propagation method eliminates the requirement for a priori known correlation kernel that is needed for a regression analysis. The signal abstraction method is applied and successfully tested for abstracting signals in the fuel control system, with high degree of interconnection between software and hardware, using data from more than 5000 connected vehicles.

Variational quantum semi-supervised classifier based on label propagation

Label propagation is an essential semi-supervised learning method based on graphs, which has a broad spectrum of applications in pattern recognition and data mining. This paper proposes a quantum semi-supervised classifier based on label propagation. Considering the difficulty of graph construction, we develop a variational quantum label propagation (VQLP) method. In this method, a locally parameterized quantum circuit is created to reduce the parameters required in the optimization. Furthermore, we design a quantum semi-supervised binary classifier based on hybrid Bell and Z bases measurement, which has a shallower circuit depth and is more suitable for implementation on near-term quantum devices. We demonstrate the performance of the quantum semi-supervised classifier on the Iris data set, and the simulation results show that the quantum semi-supervised classifier has higher classification accuracy than the swap test classifier. This work opens a new path to quantum machine learning based on graphs.

The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning.

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We design a set of inference strategies tailored towards our algorithm, named Group Loss++ that further improve the results of our model. We show state-of-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person re-identification datasets, providing a unified framework for retrieval and re-identification.

A Novel Label Propagation Method for Community Detection Based on Game Theory

Community is a mesoscopic feature of the multi-scale phenomenon of complex networks, which is the bridge to revealing the formation and evolution of complex networks. Due to high computational efficiency, label propagation becomes a topic of considerable interest within community detection, but its randomness yet produces serious fluctuations. Facing the inherent flaws of label propagation, this paper proposes a series of solutions. Firstly, this paper presents a heuristic label propagation algorithm named Label Propagation Algorithm use Cliques and Weight (LPA-CW). In this algorithm, labels are expanded from seeds and propagated based on node linkage index. Seeds are produced from complete subgraph, and node linkage index is related to neighboring nodes. This method can produce competitive modularity Q but not Normalized Mutual Information (NMI), and compensate with existing methods, such as Stepping Community Detection Algorithm based on Label Propagation and Similarity (LPA-S). Secondly, in order to combine the advantages of different algorithms, this paper introduces a game theory framework, design the profit function of the participant algorithms to attain Nash equilibrium, and build an algorithm integration model for community detection (IA-GT). Thirdly, based on the above model, this presents an algorithm, named Label Propagation Algorithm based on IA-GT model (LPA-CW-S), which integrates LPA-CW and LPA-S and solves the incompatibility between modularity and NMI. Fully tested on both computer-generated and real-world networks, this method gives better results in indicators such as modularity and NMI than existing methods, effectively resolving the contradiction between the theoretical community and the real community. Moreover, this method significantly reduces the randomness and runs faster.

Semisupervised Fault Diagnosis of Gearbox Using Weighted Graph-Based Label Propagation and Virtual Adversarial Training

Fault diagnosis of gearbox is essential for the safe operation of the modern industrial system. Recently, supervised deep learning (DL)-based approaches have rapidly developed because they can achieve an automated fault-sensitive feature extraction process. However, most DL-based methods work on the assumption that labeled data are sufficient, and the field data recorded with label information are difficult to obtain in practical industrial applications. Moreover, there is a huge amount of unlabeled data that are collected in industrial practice and they can be utilized by semisupervised learning-based methods to enhance the identification ability of the model. Therefore, a novel semisupervised method for gearboxes using weighted label propagation and virtual adversarial training (WLP-VAT) is proposed in this article. In this study, the transductive label propagation method is introduced to infer pseudo labels for the unlabeled samples, which is based on the assumption that similar samples are likely to have the same labels. Meanwhile, a sample weight reflecting the uncertainty of each pseudo label is proposed to reduce the negative effect caused by noisy labels. Moreover, VAT is adopted to further enhance the identification capability of the model under limited labeled data. The effectiveness of the proposed semisupervised approach is verified by an experimental gearbox dataset and a wind turbine gearbox dataset. The results of the above two experiments indicate that our proposed semisupervised can leverage unlabeled data to solve the labeled data shortage.

Dual global-aware propagation for few-shot learning

• A global-aware sample module (GSM) is proposed to capture the global description of each sample. • A global-aware task module (GTM) is used to obtain the global description across tasks. • A feature fusion module incorporating both global task and global sample information is used for label propagation. Few-shot learning remains a challenging problem because it needs to classify unseen categories with only a few samples as limited supervision. The tasks and samples can be extremely different in various few-shot problems, which makes it even more difficult. Due to the local connectivity in CNN, it can not capture the global description of the samples and the features are not discriminative enough from a global viewpoint. Meanwhile, a sample usually reveals similar features in different tasks, which does not consider the global information of the task and weakens the discrimination of features. To address the above issue, we proposed a Dual Global-Aware method for label Propagation (DGAP) to encode two kinds of global description to enhance the discriminative power of the learned features. On the sample level, the global-aware sample module (GSM) is employed to get the contextual description and enhance the feature representation capability of each sample. On the task level, the global-aware task module (GTM) is used to embed the features in the current task to a more appropriate and discriminative position in the feature space which is task-oriented. In the end, a feature fusion module is adopted to combine the features obtained from both global sample and global task respects. Based on the label propagation method, the proposed DGAP improves the performance approximately 2–5% over the baseline on different benchmarks (mini-Imagenet and tiered-Imagenet) across different structures (Conv4 structure and ResNet12 structure), which reaches the state-of-the-art.

The recognition of kernel research team

• The definition of local mutual degree of dependence : Inspired by Adams’s fourth elements and Axiomatic index, a local index is proposed to measure the relationships between any pair of co-authors. In contrast to node filtration through the fixed threshold, our algorithm automatically distinguishes the kernel authors; the iteration converges quickly; the output network contains a small number of authors who have published plenty of papers and get much attention. • The presence of Pareto principle in science : The statistics of co-author networks from ten research fields show that a small number of authors published the most papers and achieved the most citations in the networks, indicating the presence of the Pareto principle in co-authorship networks. • Kernel research team recognized : A fast attributed overlapping community detection method is applied to the academic networks for detecting kernel research teams. The degree distributions of these kernel teams are uniform flat than that of the communities detected by original co-authorship networks. Scientific projects are usually created by teams rather than individuals since the realizations of the projects need complex instruments and multidisciplinary cooperations. Although there is a myriad of reports on the assembly mechanisms of research teams, most are restricted to the empirical analysis of some special teams, and they failed to analyze the research team from big co-authorship networks. Inspired by L. G. Adams’s “basic elements” of the successful research team, this paper proposed a method for identifying the kernel research teams from the co-author networks. We create a database containing all articles published in the journals recommended by the China Computer Federation (CCF), based on which the networks of ten subfields in computer science are constructed. In the empirical analysis, a handful of scholars are found to contribute a large portion of literature and gather numerous citations; this proves the presence of the Pareto principle in academic networks. Furthermore, the information of 34 famous research teams is collected and analyzed; our study shows most leaders and members who belong to these 34 teams can be recovered from the network of kernel research teams even when more than 70 % of authors are removed from the original co-authorship network. Finally, in order to take full advantage of the authors’ research interests, we improve the original label propagation method to guarantee good performance in our dataset.

Semi-supervised label propagation for multi-source remote sensing image change detection

Remote sensing image change detection remains a challenging task. Most existing approaches are based on fully supervised learning, but labeled data are so scarce for change detection. It is difficult to exhibit high detection performance with a limited amount of labeled data. In this paper, we propose a semi-supervised Label Propagation (SSLP) approach for multi-source remote sensing image change detection. First, a clustering label propagation (CLP) method is designed to cluster pre and post images, respectively, and assign pseudo labels to unlabeled pixel pairs that have similar mapping relationships to labeled pixel pairs. Second, a pixel density metric is investigated to filter out the data with low density and retain the data with high density, which can ensure the reliability of the propagated data. Third, a secondary expansion method based on pixel neighborhood is used to generate enough training data for training a classifier. Finally, the effectiveness of SSLP is validated on three real datasets by comparing to other related methods.

Fairness in graph-based semi-supervised learning

Machine learning is widely deployed in society, unleashing its power in a wide range of applications owing to the advent of big data. One emerging problem faced by machine learning is the discrimination from data, and such discrimination is reflected in the eventual decisions made by the algorithms. Recent study has proved that increasing the size of training (labeled) data will promote the fairness criteria with model performance being maintained. In this work, we aim to explore a more general case where quantities of unlabeled data are provided, indeed leading to a new form of learning paradigm, namely fair semi-supervised learning. Taking the popularity of graph-based approaches in semi-supervised learning, we study this problem both on conventional label propagation method and graph neural networks, where various fairness criteria can be flexibly integrated. Our developed algorithms are proved to be non-trivial extensions to the existing supervised models with fairness constraints. Extensive experiments on real-world datasets exhibit that our methods achieve a better trade-off between classification accuracy and fairness than the compared baselines.

Partial multi-label learning via specific label disambiguation

Partial Multi-Label Learning (PML) aims to learn a robust multi-label classifier from training data, where each instance is associated with a set of candidate labels, among which only a subset of them is relevant. Some existing methods consider the noise in the feature space and have made some achievements. However, they ignored that each label might be only related to a subset of original features, and the other features might be noise in different label spaces. Such as, the similarity between two instances may be different in different label spaces, which is crucial in PML. To tackle the problem, we propose a novel framework named Partial multi-lAbel learning via Specific lAbel Disambiguation(PASAD), which tries to extract the label-specific features for disambiguation. Specifically, we first adapt the Hilbert–Schmidt Independence Criterion (HSIC) to identify the projection matrix for each label by maximizing the dependence between feature space and each label space. With these matrices, the instances can be mapped into each label-specific feature space to reduce irrelevant information. Besides, label correlations are considered to enrich the label-specific features. Afterward, we propose a specific label propagation method to estimate the labeling confidence values, which adapts the label propagation in each label-specific feature space and considers the interactions between different label spaces. We combine the two stages in an iterative manner. Finally, any binary classifier can be applied to induce a classification model by each label’s new specific features and credible labels. Tremendous experimental results demonstrate the effectiveness and superiority of our proposed method.

Multi-similarity fusion-based label propagation for predicting microbes potentially associated with diseases

More and more scholars have confirmed through research that the microbes in the human body are closely related to human health. Therefore, more and more scholars are committed to researching new prediction methods to discover potential microbe-disease associations. Newly predicted microbes associated with diseases are obtained by a novel way, namely, multi-similarity fusion-based label propagation (MDA-MSFLP). Specifically, the method firstly obtains multiple symmetric similarity matrices about microbes and diseases through calculation. Then, more comprehensive prior information is obtained by the fusion of multiple similarities with the multiple kernel learning (MKL) method. Also, it is considered that the items represented by 0 in the association matrix may be potential associations, so the association matrix is preprocessed according to the fused similarity and the corresponding items represented by 0 will be replaced by the obtained association probability scores. Finally, the label propagation method is used to make predictions for microbes which are potentially related to diseases. To verify its performance, 5-fold cross validation and leave one out cross validation are applied to MDA-MSFLP. It can be found that the results of our method are excellent. Moreover, detailed case studies of three diseases (Chronic Obstructive Pulmonary Disease (COPD), Cystic fibrosis and Psoriasis) are performed. Among the top 15 microbes associated with these three diseases in the predicted results, 10, 11, and 13 have the corresponding literature evidence. It can be concluded that MDA-MSFLP can contribute to the acquisition of microbes associated with diseases.