Meta Paths Research Articles

Clustering on heterogeneous IoT information network based on meta path.

As the Internet and Internet of Things (IoT) continue to develop, Heterogeneous Information Networks (HIN) have formed complex interaction relationships among data objects. These relationships are represented by various types of edges (meta-paths) that contain rich semantic information. In the context of IoT data applications, the widespread adoption of Trigger-Action Patterns makes the management and analysis of heterogeneous data particularly important. This study proposes a meta-path-based clustering method for heterogeneous IoT data called I-RankClus, which aims to improve the modeling and analysis efficiency of IoT data. By combining ranking with clustering algorithms, the PageRank algorithm was used to calculate the intraclass influence of objects in the network. The HITS algorithm then transfers the influence to the core objects, thereby optimizing the classification of objects during the clustering process. The I-RankClus algorithm does not process each meta-path individually, but instead integrates multiple meta-paths to enhance the interpretability and clustering performance of the model. The experimental results show that the I-RankClus algorithm can process complex IoT datasets more effectively than traditional clustering methods and provide more accurate clustering outcomes. Furthermore, through a detailed analysis of meta-paths, this study explored the influence and importance of different meta-paths, thereby validating the effectiveness of the algorithm. Overall, the research presented in this paper not only improves the application effects of HINs in IoT data analysis but also provides valuable methods and insights for future network data processing.

Mashup-oriented API recommendation via pre-trained heterogeneous information networks

Combining different Web APIs to create Mashups has become very popular nowadays. Choosing suitable ones from massive Web APIs is of vital importance for efficient Mashup creations. A number of Mashup-oriented API recommendation methods have been proposed to address this issue, but they have limitations in their ability to exploit the rich attributes and connection data of Web APIs, which impedes their performance. By modeling the API-related data as a heterogeneous information network and using pre-training technology, this paper proposes an accurate API recommendation method, named PHRec. In this method, the meta paths of APIs in the heterogeneous information network are exploited to obtain their context semantics; the method adopts an attention mechanism. Extensive experiments have been conducted with a real Web API dataset to evaluate the proposed method. The experimental results demonstrate that it significantly outperforms the state-of-the-art methods in the Web API recommendation task.

StructSim: Meta-Structure-Based Similarity Measure in Heterogeneous Information Networks

Similarity measures in heterogeneous information networks (HINs) have become increasingly important in recent years. Most measures in such networks are based on the meta path, a relation sequence connecting object types. However, in real-world scenarios, there exist many complex semantic relationships, which cannot be captured by the meta path. Therefore, a meta structure is proposed, which is a directed acyclic graph of object and relation types. In this paper, we explore the complex semantic meanings in HINs and propose a meta-structure-based similarity measure called StructSim. StructSim models the probability of subgraph expansion with bias from source node to target node. Different from existing methods, StructSim claims that the subgraph expansion is biased, i.e., the probability may be different when expanding from the same node to different nodes with the same type based on the meta structure. Moreover, StructSim defines the expansion bias by considering two types of node information, including out-neighbors of current expanded nodes and in-neighbors of next hop nodes to be expanded. To facilitate the implementation of StructSim, we further designed the node composition operator and expansion probability matrix with bias. Extensive experiments on DBLP and YAGO datasets demonstrate that StructSim is more effective than the state-of-the-art approaches.

Effect of similarity measures in diffusion prediction on homogeneous and heterogeneous bibliographic network

This paper evaluates the effect of similarity measures in predicting diffusion on homogeneous and heterogeneous bibliographic networks. The bibliographic network is analyzed within a homogeneous network and heterogeneous network, where a co-author relationship exists for the former, and multiple types of meta paths are considered for the latter. The supervised learning method is used to predict whether a node will be active with a topic or not. The features are extracted as the activation probability of a node, which represents the maximum of the activation probabilities of the neighbors of this node. In a homogeneous network, the activation probability from the activated node to the inactive node is measured based on one relationship co-author with basic similarity measures while it can be calculated based on diverse meta paths with dissimilar meta path-based similarity measures in the heterogeneous network. We performed our analysis on three different datasets. Our experimental results show that diffusion prediction in bibliographic networks provides better accuracy among heterogeneous networks than among homogeneous networks and that the Bayesian similarity measure provides the best efficiency.

Clustered Task-Aware Meta-Learning by Learning From Learning Paths.

To enable effective learning of new tasks with only a few examples, meta-learning acquires common knowledge from the existing tasks with a globally shared meta-learner. To further address the problem of task heterogeneity, recent developments balance between customization and generalization by incorporating task clustering to generate task-aware modulation to be applied to the global meta-learner. However, these methods learn task representation mostly from the features ofinput data, while the task-specific optimization process with respect to the base-learner is often neglected. In this work, we propose a Clustered Task-Aware Meta-Learning (CTML) framework with task representation learned from both features and learning paths. We first conduct rehearsed task learning from the common initialization, and collect a set of geometric quantities that adequately describes this learning path. By inputting this set of values into a meta path learner, we automatically abstract path representation optimized for downstream clustering and modulation. Aggregating the path and feature representations results in an improved task representation. To further improve inference efficiency, we devise a shortcut tunnel to bypass the rehearsed learning process at a meta-testing time. Extensive experiments on two real-world application domains: few-shot image classification and cold-start recommendation demonstrate the superiority of CTML compared to state-of-the-art methods. We provide our code at https://github.com/didiya0825.

The node importance evaluation method based on graph convolution in multilayer heterogeneous networks

ABSTRACT Node importance evaluation is a hot issue in complex network analysis. Existing node importance evaluation methods are mainly oriented to homogeneous networks, which ignore the heterogeneity of node types and edges. We propose an MLN critical node evaluation method based on graph convolution. In this paper, we generate the feature matrix of nodes. Considering the diversity of node types in the network, we design an adapted node sampling method based on the meta path. An MLN node embedding model is constructed based on a graph convolutional network (MGC). Besides, the negative sampling technique is used to complete MGC training. Metrics of critical node evaluation are constructed by combining the node embedding vectors and local structural features to evaluate the node's importance. The experimental results show that the proposed method has better evaluation accuracy than the K-Shell algorithm (K-Shell), K-shell-based gravity model ranking algorithm (KSDG), the Page Rank algorithm in MLN (PR), influence maximization based on network embedding (IMNE) and the node ranking algorithm based on information entropy (ERM).

Modeling Selection for Credit Risk Measurement: Based on Meta Path Features

Modeling Selection for Credit Risk Measurement: Based on Meta Path Features

End-to-end interpretable disease-gene association prediction.

Identifying disease-gene associations is a fundamental and critical biomedical task towards understanding molecular mechanisms, the diagnosis and treatment of diseases. It is time-consuming and expensive to experimentally verify causal links between diseases and genes. Recently, deep learning methods have achieved tremendous success in identifying candidate genes for genetic diseases. The gene prediction problem can be modeled as a link prediction problem based on the features of nodes and edges of the gene-disease graph. However, most existing researches either build homogeneous networks based on one single data source or heterogeneous networks based on multi-source data, and artificially define meta-paths, so as to learn the network representation of diseases and genes. The former cannot make use of abundant multi-source heterogeneous information, while the latter needs domain knowledge and experience when defining meta-paths, and the accuracy of the model largely depends on the definition of meta-paths. To address the aforementioned challenges above bottlenecks, we propose an end-to-end disease-gene association prediction model with parallel graph transformer network (DGP-PGTN), which deeply integrates the heterogeneous information of diseases, genes, ontologies and phenotypes. DGP-PGTN can automatically and comprehensively capture the multiple latent interactions between diseases and genes, discover the causal relationship between them and is fully interpretable at the same time. We conduct comprehensive experiments and show that DGP-PGTN outperforms the state-of-the-art methods significantly on the task of disease-gene association prediction. Furthermore, DGP-PGTN can automatically learn the implicit relationship between diseases and genes without manually defining meta paths.

An optimal model for domain specific named entity linking with heterogeneous information networks

In this web era, entity linking plays a major role. In the web the information’s are associated with different kinds of data and objects. Heterogeneous information networks (HIN) involved multi composed interlinked interconnected objects with various types of connections which is more prominent in this real world. Most of the research work focused towards processing homogeneous networks as well as linking entities with Wikipedia as knowledge base. In this paper we proposed a probabilistic based domain specific entity linking system that will link named entity mentions detected from unstructured web text corpus with corresponding entity in the existing domain specific Heterogeneous information networks as knowledge base. This work is most challenging due to entity name ambiguity as well as knowledge in the network that are limited one. The proposed model framework presents a model that will link named entity from unstructured web text with domain specific Heterogeneous information network mainly focuses on to learn the weight of meta path. The experiments are done over real world dataset such as DBLP and IMDB dataset.

Sparse representation for heterogeneous information networks

A complex network is a fundamental tool to describe real-world complex systems, with most real-world systems containing multiple object types and relationships that can be described as heterogeneous information networks. However, with the increasing network complexity, understanding the complex patterns and finding the meta paths or meta-structures of the heterogeneous information networks has become challenging. This paper proposes a sparse representation for heterogeneous information networks and extracts the heterogeneous information atoms that describe the basic connection pattern of the original heterogeneous information network. The heterogeneous information atoms help extract the main meta-paths or meta-structures and understand the complex patterns of the original heterogeneous information network. Furthermore, the heterogeneous information networks can be decomposed, dimension-reduced, and reconstructed through the heterogeneous information atoms. Extensive experimental results demonstrate that heterogeneous information atoms and sparse coding represent the basic connection pattern of real-world heterogeneous information networks. Indeed, the developed method can reconstruct a network with a recovery exceeding 90%.

ASIAM-HGNN: Automatic Selection and Interpretable Aggregation of Meta-Path Instances for Heterogeneous Graph Neural Network

In heterogeneous information network (HIN)-based applications, the existing methods usually use Heterogeneous Graph Neural Networks (HGNN) to handle some complex tasks. However, these methods still have some shortcomings: 1) they manually pre-select some meta-paths and thus some important ones are missing, while the missing ones still contains the information and features of the node in the entire graph structure; and 2) they have no high interpretability since they do not consider the logical sequences in an HIN. In order to deal with them, we propose ASIAM-HGNN: a heterogeneous graph neural network combined with the automatic selection and interpretable aggregation of meta-path instances. Our model can automatically filter important meta paths for each node, while preserving the logical sequence between nodes, so as to solve the problems existing in other models. A group of experiments are conducted on real-world datasets, and the results demonstrate that the models learned by our method have a better performance in most of task scenarios.

Enhancing Performance of Movie Recommendations Using LSTM With Meta Path Analysis

Enhancing Performance of Movie Recommendations Using LSTM With Meta Path Analysis

Feature’s importance assessment for activation probability measure in topic’s diffusion prediction

In this study, we aim to estimate the sigma coefficient in the activation probability calculation for a topic’s diffusion prediction problem. In our previous studies, we proposed an aggregated activation probability combination of the metapath and text information, in which sigma is the characteristic coefficient of interest’s similarity based on textual content. σ is a parameter that controls the rates of the influence of active probability based on the metapath and interest similarity on aggregated activation probability. In a previous study, we supposed the equal importance between the metapath and textual information, when σ = 0.5. However, for different datasets, this coefficient differs, depending on the meaning of the meta-path and the textual information. In this study, we continue to investigate the importance of the sigma coefficient for the effectiveness of the topic’s diffusion prediction problem on the bibliographic network. We propose to utilize the two most common methods for feature selection: the ANOVA test and mutual information to obtain the significance of two features MP (metapath) and the IS (textual information). The experimental results show that the use of the feature selection methods to estimate the sigma coefficient is reliable and improves the predictive performance of the topic’s diffusion compared with the standard assignment of 0.5.

An Overview of Heterogeneous Information Networks based on Recommendation System

Heterogeneous Information Networks (HINs) provide a natural way to represent different relationships among entities of different kinds, as a consequence they are valuable in many domains. Analysing and extracting understanding from HINs normally is based at the idea of meta paths, which are paths in the community schema denoting family members of different semantics among entities. Moreover, real-global HINs are frequently extremely big, containing thousands and thousands of nodes and edges. Therefore, exploring and analysing HINs not only requires interdisciplinary knowhow, having the ability both to interpret and pick out suitable meta paths inside the network, but additionally to run the analysis in an efficient and scalable manner. However, there may be a loss of tools to facilitate this assignment. Most real system include a huge wide variety of interacting, multityped components, while most current researches version them as homogeneous networks, without distinguishing different forms of objects and links in the networks. In recent years, an increasing amount of works have been proposed to present helper data in recommender system to alleviate information sparsity and cold-start issues. Among them, heterogeneous information networks (HIN)- based recommender systems give a brought together way to deal with meld different helper data, which can be joined with standard suggestion calculations to successfully upgrade the presentation and interpretability of models, and accordingly have been applied in many kinds of recommendation tasks. This paper gives a far reaching and efficient overview of HIN-based recommender systems, including four perspectives: ideas, strategies, applications, and resources.

A Meta Path Based Method for Entity Set Expansion in Knowledge Graph

Entity Set Expansion (ESE) is the problem that expands a small set of seed entities into a more complete set, entities of which have common traits. As a popular data mining task, ESE has been widely used in many applications, such as dictionary construction, query suggestion and new brand identification. Existing ESE methods mainly utilize text and Web information. That is, the intrinsic relation among entities is inferred from their occurrences in text or Web. With the surge of knowledge graph in recent years, it is possible to extend entities according to their occurrences in knowledge graph. In this paper, we consider the knowledge graph as a heterogeneous information network (HIN) that contains different types of objects and links, and propose a novel method, called MP_ESE, to extend entities in the HIN. The MP_ESE employs meta paths, a relation sequence connecting entities, in HIN to capture the implicit common traits of seed entities. In addition, an automatic meta path generation method, called SMPG, has been designed to exploit the potential relations among entities. Heuristic learning and PU learning methods are employed to learn the weights of extracted meta paths. With these generated and weighted meta paths, the MP_ESE can effectively extend entities. Comprehensive experiments on real datasets show the effectiveness and efficiency of MP_ESE.

메타경로분석을 이용한 미시체계 내 방어행동 관련 요인 간의 구조적 관계

In this study, from the point of view of the ecological systems model, meta path analysis was performed on the correlations among the peer relationships, anti-bullying, school culture, and social-emotional competence in the micro-system. Through this, we suspected the significance of direct and indirect effects between the factors in the path towards defending behaviors, by anti-bullying school culture and peer relationships, environmental variables, mediating social emotional competence, and personal variables. To do this, the meta-path analysis was conducted on domestic academic journals (33 articles), master's and doctoral dissertations, and candidate journals (29 articles) from January 2007 to June 2021 (total 62 articles). In the meta path analysis, direct effects were found in all paths among all factors of the peer relationships, anti-bullying school culture, social-emotional competence, and defending behaviors. In addition, mediating effects were found in social emotional competence factors between peer relationships and defending behaviors, and between the anti-bullying school culture and defending behaviors respectively. As a result of this, it is implied that students who develop a high level of social-emotional competence based on their peer relationships and anti-bullying school culture tend to show a higher frequency of defending behaviors in school violence environments.

Learning representation of heterogeneous temporal graphs for recommendation

Heterogeneous temporal graphs are important abstractions for organising data in recommender systems, for which an effective representation learning method is presented in this paper. Specifically, an attention-based two-stage aggregation technique is adopted to aggregate the message passed over each edge. The aggregation stage first involves temporal aggregation for each group of neighbouring nodes connected by the same type of edges. Then a further aggregation is performed among the aggregated results of each edge type. The method can capture the temporal evolution patterns of heterogeneous temporal graphs in continuous time-space and model the graphs' heterogeneity without requiring predefined meta paths. Experimental results on public recommendation datasets demonstrate that the recommendation algorithm based on the representation learning method outperforms the state-of-the-art baselines.

BioERP: biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions.

Predicting entity relationship can greatly benefit important biomedical problems. Recently, a large amount of biomedical heterogeneous networks (BioHNs) are generated and offer opportunities for developing network-based learning approaches to predict relationships among entities. However, current researches slightly explored BioHNs-based self-supervised representation learning methods, and are hard to simultaneously capturing local- and global-level association information among entities. In this study, we propose a BioHN-based self-supervised representation learning approach for entity relationship predictions, termed BioERP. A self-supervised meta path detection mechanism is proposed to train a deep Transformer encoder model that can capture the global structure and semantic feature in BioHNs. Meanwhile, a biomedical entity mask learning strategy is designed to reflect local associations of vertices. Finally, the representations from different task models are concatenated to generate two-level representation vectors for predicting relationships among entities. The results on eight datasets show BioERP outperforms 30 state-of-the-art methods. In particular, BioERP reveals great performance with results close to 1 in terms of AUC and AUPR on the drug-target interaction predictions. In summary, BioERP is a promising bio-entity relationship prediction approach. Source code and data can be downloaded from https://github.com/pengsl-lab/BioERP.git. Supplementary data are available at Bioinformatics online.

DeepR2cov: deep representation learning on heterogeneous drug networks to discover anti-inflammatory agents for COVID-19.

Recent studies have demonstrated that the excessive inflammatory response is an important factor of death in coronavirus disease 2019 (COVID-19) patients. In this study, we propose a deep representation on heterogeneous drug networks, termed DeepR2cov, to discover potential agents for treating the excessive inflammatory response in COVID-19 patients. This work explores the multi-hub characteristic of a heterogeneous drug network integrating eight unique networks. Inspired by the multi-hub characteristic, we design 3 billion special meta paths to train a deep representation model for learning low-dimensional vectors that integrate long-range structure dependency and complex semantic relation among network nodes. Based on the representation vectors and transcriptomics data, we predict 22 drugs that bind to tumor necrosis factor-α or interleukin-6, whose therapeutic associations with the inflammation storm in COVID-19 patients, and molecular binding model are further validated via data from PubMed publications, ongoing clinical trials and a docking program. In addition, the results on five biomedical applications suggest that DeepR2cov significantly outperforms five existing representation approaches. In summary, DeepR2cov is a powerful network representation approach and holds the potential to accelerate treatment of the inflammatory responses in COVID-19 patients. The source code and data can be downloaded from https://github.com/pengsl-lab/DeepR2cov.git.

Fine-Grained User Location Prediction using Meta-Path Context with Attention Mechanism

The prevalence of Location-Based Social Networks (LBSNs) significantly improves the location-aware capability of services by providing Geo-tagged information. Relied on a great number of user check-in data in the location-based social networks, their essential mobility modes are able to be comprehensively studied, which is basic for forecasting the next venue where a specific user is going to visit considering his relevant historical check-in data. Since there exist different kinds of nodes and interactions between nodes, these information could be look upon as a network that is made up of heterogeneous information. In this network a few of different semantic meta paths could be obtained. Enlightened from the competitive advantage of embedding method relied upon meta-path contexts in the heterogeneous information network, we study a joint deep learning scheme exploring different meta-path context information to forecast fine-grained location. In order to capture different semantics in a user-location interaction, we adopt a simple but high-efficient attention method to learn the meta-path importance or weights. In the terms of model optimization, considering we have only positive sample data and there exists intrinsically latent feedback in check-in information, herein a pairwise learning method is utilized for maximizing the margin between visited and invisible venues. Experiment in different data-sets validate the competitive performance of the suggested approach under different assessment criterion.