Multiple Types Of Relationships Research Articles

RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature.

In the field of biomedical text mining, the ability to extract relations from the literature is crucial for advancing both theoretical research and practical applications. There is a notable shortage of corpora designed to enhance the extraction of multiple types of relations, particularly focusing on proteins and protein-containing entities such as complexes and families, as well as chemicals. In this work, we present RegulaTome, a corpus that overcomes the limitations of several existing biomedical relation extraction (RE) corpora, many of which concentrate on single-type relations at the sentence level. RegulaTome stands out by offering 16 961 relations annotated in >2500 documents, making it the most extensive dataset of its kind to date. This corpus is specifically designed to cover a broader spectrum of >40 relation types beyond those traditionally explored, setting a new benchmark in the complexity and depth of biomedical RE tasks. Our corpus both broadens the scope of detected relations and allows for achieving noteworthy accuracy in RE. A transformer-based model trained on this corpus has demonstrated a promising F1-score (66.6%) for a task of this complexity, underscoring the effectiveness of our approach in accurately identifying and categorizing a wide array of biological relations. This achievement highlights RegulaTome's potential to significantly contribute to the development of more sophisticated, efficient, and accurate RE systems to tackle biomedical tasks. Finally, a run of the trained RE system on all PubMed abstracts and PMC Open Access full-text documents resulted in >18 million relations, extracted from the entire biomedical literature.

Multiplex Network Representation Learning Based on Graph Neural Network

Network representation learning is receiving increasing attention from scholars. Among them, methods based on graph neural networks have become particularly popular. However, most existing methods currently only focus on networks with a single type of relations. In the real world, networks contain a wealth of diverse information, with multiple types of relationships between nodes. In this paper, we propose a graph neural network-based multiplex network representation learning model (GNMRL). We model nodes within each layer of the multiplex network by aggregating neighbor information. Additionally, since nodes are influenced by different network layers, we integrate node interaction information across network layers. We conducted systematic experiments on four datasets, and the results show that GNMRL outperforms other comparison methods in both link prediction and node classification tasks.

Estimating disease heritability from complex pedigrees allowing for ascertainment and covariates

We propose TetraHer, a method for estimating the liability heritability of binary phenotypes. TetraHer has five key features. First, it can be applied to data from complex pedigrees that contain multiple types of relationships. Second, it can correct for ascertainment of cases or controls. Third, it can accommodate covariates. Fourth, it can model the contribution of common environment. Fifth, it produces a likelihood that can be used for significance testing. We first demonstrate the validity of TetraHer on simulated data. We then use TetraHer to estimate liability heritability for 229 codes from the tenth International Classification of Diseases (ICD-10). We identify 107 codes with significant heritability (p<0.05/229), which can be used in future analyses for investigating the genetic architecture of human diseases.

Applying precision medicine principles to the management of multimorbidity: the utility of comorbidity networks, graph machine learning, and knowledge graphs.

The current management of patients with multimorbidity is suboptimal, with either a single-disease approach to care or treatment guideline adaptations that result in poor adherence due to their complexity. Although this has resulted in calls for more holistic and personalized approaches to prescribing, progress toward these goals has remained slow. With the rapid advancement of machine learning (ML) methods, promising approaches now also exist to accelerate the advance of precision medicine in multimorbidity. These include analyzing disease comorbidity networks, using knowledge graphs that integrate knowledge from different medical domains, and applying network analysis and graph ML. Multimorbidity disease networks have been used to improve disease diagnosis, treatment recommendations, and patient prognosis. Knowledge graphs that combine different medical entities connected by multiple relationship types integrate data from different sources, allowing for complex interactions and creating a continuous flow of information. Network analysis and graph ML can then extract the topology and structure of networks and reveal hidden properties, including disease phenotypes, network hubs, and pathways; predict drugs for repurposing; and determine safe and more holistic treatments. In this article, we describe the basic concepts of creating bipartite and unipartite disease and patient networks and review the use of knowledge graphs, graph algorithms, graph embedding methods, and graph ML within the context of multimorbidity. Specifically, we provide an overview of the application of graph theory for studying multimorbidity, the methods employed to extract knowledge from graphs, and examples of the application of disease networks for determining the structure and pathways of multimorbidity, identifying disease phenotypes, predicting health outcomes, and selecting safe and effective treatments. In today's modern data-hungry, ML-focused world, such network-based techniques are likely to be at the forefront of developing robust clinical decision support tools for safer and more holistic approaches to treating older patients with multimorbidity.

Clustering Enhanced Multiplex Graph Contrastive Representation Learning.

Multiplex graph representation learning has attracted considerable attention due to its powerful capacity to depict multiple relation types between nodes. Previous methods generally learn representations of each relation-based subgraph and then aggregate them into final representations. Despite the enormous success, they commonly encounter two challenges: 1) the latent community structure is overlooked and 2) consistent and complementary information across relation types remains largely unexplored. To address these issues, we propose a clustering-enhanced multiplex graph contrastive representation learning model (CEMR). In CEMR, by formulating each relation type as a view, we propose a multiview graph clustering framework to discover the potential community structure, which promotes representations to incorporate global semantic correlations. Moreover, under the proposed multiview clustering framework, we develop cross-view contrastive learning and cross-view cosupervision modules to explore consistent and complementary information in different views, respectively. Specifically, the cross-view contrastive learning module equipped with a novel negative pairs selecting mechanism enables the view-specific representations to extract common knowledge across views. The cross-view cosupervision module exploits the high-confidence complementary information in one view to guide low-confidence clustering in other views by contrastive learning. Comprehensive experiments on four datasets confirm the superiority of our CEMR when compared to the state-of-the-art rivals.

Spatio-Temporal Heterogeneous Graph-Based Convolutional Networks for Traffic Flow Forecasting

Traffic flow forecasting plays a crucial role in the construction of intelligent transportation. The aims of this paper are to fully exploit the spatial correlation between nodes in a traffic network and to compensate for the inability of graph-based deep learning methods to model multiple relationship types, resulting in inadequate extraction of spatially correlated information about the traffic network. In this paper, we propose a deep spatio-temporal recurrent evolution network based on the graph convolution network (STREGCN) for heterogeneous graphs. Specifically, we transform the traffic network into a multi-relational heterogeneous graph to improve the information representation of the graph. This allows our model to capture multiple types of spatially relevant information. In the temporal dimension, we use one-dimensional causal convolution based on the gated linear unit to extract the temporal correlation information of the traffic flow. In addition, we designed the output of the spatio-temporal convolution module to obtain the final traffic flow predictions after a fully connected layer. Experiments on real datasets illustrate the effectiveness of the proposed STREGCN model and show the importance of representing information through heterogeneous graphs for the task of traffic flow prediction.

Discrete-Time Quantum Walk on Multilayer Networks.

A Multilayer network is a potent platform that paves the way for the study of the interactions among entities in various networks with multiple types of relationships. This study explores the dynamics of discrete-time quantum walks on a multilayer network. We derive a recurrence formula for the coefficients of the wave function of a quantum walker on an undirected graph with a finite number of nodes. By extending this formula to include extra layers, we develop a simulation model to describe the time evolution of the quantum walker on a multilayer network. The time-averaged probability and the return probability of the quantum walker are studied with Fourier, and Grover walks on multilayer networks. Furthermore, we analyze the impact of decoherence on quantum transport, shedding light on how environmental interactions may impact the behavior of quantum walkers on multilayer network structures.

Past 6-Month Prevalence of IPV Victimization among Transgender and Gender-Diverse Undergraduate Students: A Brief Report.

Research has largely neglected the issue of intimate partner violence (IPV) among transgender and gender-diverse (TGD; e.g., nonbinary and genderqueer) individuals. However, existing research suggests that TGD individuals are disproportionately affected by IPV. The current study sought to explore if and how rates of IPV vary among subgroups of TGD undergraduate students and contextual factors of IPV among TGD individuals including the co-occurrence of multiple forms of IPV victimization, the type of relationship in which IPV occurred, and the gender identity of the IPV perpetrator. Participants were 280 TGD undergraduate students attending 20 medium- and large-sized residential public universities across the contiguous United States. Of the entire sample of TGD undergraduate students (N = 280), a total of 27.5% endorsed past 6-month IPV victimization (20.0% psychological, 6.1% physical, 8.9% sexual, 11.4% coercive control, and 5.7% LGBTQIA+-specific). Among only the participants who endorsed past 6-month IPV victimization (N = 77), 45.4% reported one form of IPV victimization, 26.0% two forms, 22.1% three forms, and 6.5% four forms. Further, 41.3% of TGD IPV victims were in a casual relationship, 56.0% were in a serious relationship, and 2.7% were in multiple relationship types. Finally, 55.8% of victims reported their perpetrator was a man, 22.1% a woman, and 22.1% a TGD individual. No significant differences in rates of IPV were found between TGD respondents. These data highlight the urgent need for programming efforts on college campuses that are specifically designed to prevent and address IPV among and against TGD students. Future research should evaluate universal- and population-specific risk and protective factors for IPV among TGD individuals to inform prevention and response efforts for this highly vulnerable population.

Clustering of multi-layer networks with structural relations and conservation of features

Multi-layer networks are omnipresent in nature and society, as complex systems often involve multiple types of relationships among entities. Compared with single-layer graphs, community detection is a challenging task that requires simultaneous characterization of the structure and relations across various layers. Current algorithms have been criticized for their suboptimal performance in describing and quantifying the structure of communities in multi-layer networks. A novel algorithm, called McNMF, is proposed to detect the conserved communities in multi-layer networks, where the shared and layer-specific features of vertices are learned simultaneously by utilizing joint nonnegative matrix factorization. Specifically, McNMF joins the feature learning, feature decomposition, and relation of the shared and layer-specific features into an overall objective function, thereby enhancing the quality of features. To learn the features of vertices, McNMF jointly factorizes matrices associated with multi-layer networks by projecting the topology into different basis spaces. It then decomposes the learned features into shared and layer-specific parts, enabling quantification of multi-layer network specificity at the feature level. Moreover, the relation between the shared and layer-specific features of vertices is measured using trace optimization, providing a comprehensive strategy to characterize the structure of conserved communities in multi-layer networks. Extensive experiments on artificial and real-world multi-layer networks demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of accuracy.

Multi-relational graph convolutional networks: Generalization guarantees and experiments

The class of multi-relational graph convolutional networks (MRGCNs) is a recent extension of standard graph convolutional networks (GCNs) to handle heterogenous graphs with multiple types of relationships. MRGCNs have been shown to yield results superior than traditional GCNs in various machine learning tasks. The key idea is to introduce a new kind of convolution operated on tensors that can effectively exploit correlations exhibited in multiple relationships. The main objective of this paper is to analyze the algorithmic stability and generalization guarantees of MRGCNs to confirm the usefulness of MRGCNs. Our contributions are of three folds. First, we develop a matrix representation of various tensor operations underneath MRGCNs to simplify the analysis significantly. Next, we prove the uniform stability of MRGCNs and deduce the convergence of the generalization gap to support the usefulness of MRGCNs. The analysis sheds lights on the design of MRGCNs, for instance, how the data should be scaled to achieve the uniform stability of the learning process. Finally, we provide experimental results to demonstrate the stability results.

Semiotic and Cultural Analysis on Local Product Brand Name

To create strategically relevant and significant brand names, factors such as culture is one of the most powerful and immediate ways to communicate an identity-image and linkage to the consumer. Thus, enables potential buyers to relate by delivering brand communication value of the brand by inspiring or persuading them by certain images and associations. However, interpretation of each brand name can be tricky as manipulation of social interaction as well as multiple types of relationships with the brands; leading to varying brand images (noise). The aims of this research were to explore cultural aspects and their meaning as brand communication value of 50 local brand names of various products as a purposeful communicative act in branding strategy. The brand names were sampled limited on a simple random sampling selected from billboard advertisement. Content analysis method through Charles Sanders Peirce’s semiotic model was used in this analysis to describe and analyse the connotation, denotation, concepts, and relationships in making inferences about the cultural messages imprinted on the brand names. The findings indicated culture still can be a source of influence in brand naming strategies. Malay language and terms by the usage of local names giving local value expression that need to be taken into account in basic strategy of brand-building as future reference. This is the consumer self-image in branding, while behind cultural expression usually lies religious motivation to influence formation of a consumer behavior such as stressing out the use of Arabic terms and Jawi script. Therefore, the study gives more insight on the brand name patterns and culture as symbolic meaning which created emotional ties of brand preference. And, the decision-making process can be much easier for producers or marketers in strategizing brand names, especially for local markets that need to be tailored to target the local community.

Dynamic Community Detection for Brain Functional Networks During Music Listening With Block Component Analysis

The human brain can be described as a complex network of functional connections between distinct regions, referred to as the brain functional network. Recent studies show that the functional network is a dynamic process and its community structure evolves with time during continuous task performance. Consequently, it is important for the understanding of the human brain to develop dynamic community detection techniques for such time-varying functional networks. Here, we propose a temporal clustering framework based on a set of network generative models and surprisingly it can be linked to Block Component Analysis to detect and track the latent community structure in dynamic functional networks. Specifically, the temporal dynamic networks are represented within a unified three-way tensor framework for simultaneously capturing multiple types of relationships between a set of entities. The multi-linear rank- (Lr, Lr, 1) block term decomposition (BTD) is adopted to fit the network generative model to directly recover underlying community structures with the specific evolution of time from the temporal networks. We apply the proposed method to the study of the reorganization of the dynamic brain networks from electroencephalography (EEG) data recorded during free music listening. We derive several network structures ( Lr communities in each component) with specific temporal patterns (described by BTD components) significantly modulated by musical features, involving subnetworks of frontoparietal, default mode, and sensory-motor networks. The results show that the brain functional network structures are dynamically reorganized and the derived community structures are temporally modulated by the music features. The proposed generative modeling approach can be an effective tool for describing community structures in brain networks that go beyond static methods and detecting the dynamic reconfiguration of modular connectivity elicited by continuously naturalistic tasks.

Profile‐pseudo likelihood methods for community detection of multilayer stochastic block models

The multilayer stochastic block model is one of the fundamental models in multilayer networks and is often used to represent multiple types of relations between different individuals. In this paper, we extend the profile‐pseudo likelihood method for the single‐layer stochastic block model to the case of the multilayer stochastic block model. Specifically, by assuming all network layers have identical community membership labels, we investigate the multilayer stochastic block model with a common community structure. In this paper, we develop a profile‐pseudo likelihood algorithm to fit a multilayer stochastic block model and estimate the community label. Meantime, we prove that the algorithm has convergence guarantee and that the estimated community label is strongly consistent. Further, for estimating the number of communities , we extend the corrected Bayesian information criterion to multilayer stochastic block models. We also extend this algorithm to fit the multilayer degree‐corrected stochastic block model. Both simulation studies and real‐world data examples indicate that the proposed method works well.

Information Extraction from the Text Data on Traditional Chinese Medicine: A Review on Tasks, Challenges, and Methods from 2010 to 2021.

Background The practice of traditional Chinese medicine (TCM) began several thousand years ago, and the knowledge of practitioners is recorded in paper and electronic versions of case notes, manuscripts, and books in multiple languages. Developing a method of information extraction (IE) from these sources to generate a cohesive data set would be a great contribution to the medical field. The goal of this study was to perform a systematic review of the status of IE from TCM sources over the last 10 years. Methods We conducted a search of four literature databases for articles published from 2010 to 2021 that focused on the use of natural language processing (NLP) methods to extract information from unstructured TCM text data. Two reviewers and one adjudicator contributed to article search, article selection, data extraction, and synthesis processes. Results We retrieved 1234 records, 49 of which met our inclusion criteria. We used the articles to (i) assess the key tasks of IE in the TCM domain, (ii) summarize the challenges to extracting information from TCM text data, and (iii) identify effective frameworks, models, and key findings of TCM IE through classification. Conclusions Our analysis showed that IE from TCM text data has improved over the past decade. However, the extraction of TCM text still faces some challenges involving the lack of gold standard corpora, nonstandardized expressions, and multiple types of relations. In the future, IE work should be promoted by extracting more existing entities and relations, constructing gold standard data sets, and exploring IE methods based on a small amount of labeled data. Furthermore, fine-grained and interpretable IE technologies are necessary for further exploration.

MNERLP-MUL: Merged node and edge relevance based link prediction in multiplex networks

In multiplex networks, nodes can have multiple types of relationships (links) encoded into different layers such that each layer represents a single type of link. Even though the nature of links in different layers may differ, the nodes themselves remain the same, and so do their underlying relations among themselves. Combining the information in all the layers into one single network such that link prediction can be performed using all the available information is an ongoing research problem. In this work, we theorize that to accurately perform this link prediction, we have to take into account the relevance of both the edges as well as the nodes that connect two directly unconnected nodes. First, we utilize an aggregation model that encodes the information from different layers into one summarized weighted static network, taking into account the relative density of the layers themselves. Then, we propose an algorithm, MNERLP−MUL, which first calculates node and edge relevance based on the summarized graph, and then we combine both these factors to perform link prediction on unconnected pairs of nodes. The edge relevance is calculated using the information from the immediate vicinity of the edge (local information), while node relevance is calculated based on the node’s importance to the overall structure of the graph (global information). We use this methodology to model our method on quasi-local link prediction approaches, which attempt to inculcate properties of both local and global properties for increased accuracy. We compare our method with classical link prediction methods for weighted graphs, and the results indicate its superior performance, both on the summarized weighted graph and original layers.

Community detection for multilayer weighted networks

Multilayer networks are used to encode multiple types of relations arising in complex systems and have received significant attention in recent years. Community detection in multilayer networks is an important issue in various fields; hence, stochastic block models have emerged as a popular probabilistic framework over the past decades. However, stochastic block models are suited to binary networks rather than weighted networks. A generalised stochastic block model is proposed herein to address multilayer sparse or dense weighted networks. A variational expectation-maximisation algorithm is derived to estimate the parameters of interest. In addition, an upper bound is derived for the probability of misclassification, which is governed by the Rényi divergence of order 12. Furthermore, our model is compared with four competing methods on synthetic networks. Finally, our approach is examined on financial markets and bicycle sharing systems.

Surviving Senior Psychopathy: Informant Reports of Deceit and Antisocial Behavior in Multiple Types of Relationships.

A prevailing view among researchers and mental health clinicians is that symptoms of antisocial personality disorder (ASPD)/psychopathy decrease as affected individuals reach middle age. In the current investigation, informants were surveyed about the behavior of individuals who they believed showed traits of ASPD/psychopathy and were over the age of 50. A final sample of 1,215 respondents rated the index individuals according to the ASPD/psychopathy traits derived from the pre-publication first draft of the Diagnostic and Statistical Manual of Mental Disorders Fifth Edition, revealing high endorsement of traits associated with ASPD. Survey respondents reported their observations that individuals who met a threshold for putative ASPD/psychopathy continued to engage in antisocial behavior after age 50, and as a result the respondents endured significant harm, including material losses, financial losses, and various self-reported mental health problems. Those who knew the index individuals both before and after the age of 50 were specifically asked whether there was a change in the individual's engagement in manipulation, deceit, and antisocial behavior; 93% of respondents reported that the behavior was just as bad or worse after age 50. Other researchers have suggested that the DSM diagnostic criteria do not accurately describe ASPD/psychopathy symptoms and behavior in older adults, and that the disorder remains stable, but its manifestation changes with age. This study supports those conclusions.

Brexit and Western Balkans

This article analyses effects of Brexit on relations between the United Kingdom and the Western Balkan countries (Albania, Bosnia and Herzegovina, Kosovo, Montenegro, North Macedonia, and Serbia). First, the symbolism of the UK departure from the EU for the Western Balkans is explained. In the following step, multiple types of relations (in trade, security, culture) between the post-Brexit UK and this region are analysed using the theoretical concepts of linkage, leverage and soft power. Finally, the consequences of Brexit on further EU enlargement are presented. The research has confirmed the initial hypotheses. First, as expected, the volume and density of UK-Western Balkan relations will be reduced after Brexit. Second, Western Balkans is of a very limited interest for the UK, primarily in security. Third, Brexit has not in a serious way changed the already existing low chances of EU accession for the Western Balkan countries. The reason for this has little to do with the UK’s presence in or absence from the EU and is rather a consequence of the majority view within the Union (that Britain had already shared before Brexit) concerning further enlargement and low level of preparation of Western Balkan countries for EU membership.

Multi-view Graph Attention Network for Travel Recommendation

As an e-commerce feature, the recommender system can enhance the consumer shopping experience and create huge benefits for businesses. The e-tourism has become one of the largest service industries with the application and popularity of recommender systems. Many studies have confirmed that the travel product recommendation is widely different from traditional recommendations. Due to the financial and time costs, travel products are usually browsed and purchased relatively infrequently compared with other traditional products (e.g., books, movies and food). In addition, choosing the appropriate travel product will be influenced by many factors, such as departure, destination and price. To tackle this challenging problem, we propose a MV-GAN (short for Multi-View Graph Attention Network for travel recommendation) model. It enriches user and product semantics through both metapath-guided neighbors aggregation and multi-view fusion in heterogeneous travel product recommendation graph. In particular, we design node-level and path-level attention networks for learning user and product representations from every single view. To collaboratively integrate multiple types of relationships in different views, a view-level attention mechanism is proposed to aggregate the node representations and obtain global user and product representations. We evaluate the proposed method on a public dataset and a dataset constructed from a large tourism e-commerce website in China. Extensive experiments not only validate the effectiveness of MV-GAN, but also show its potentially good interpretability.

Points-of-interest relationship inference with spatial-enriched graph neural networks

As a fundamental component in location-based services, inferring the relationship between points-of-interests (POIs) is very critical for service providers to offer good user experience to business owners and customers. Most of the existing methods for relationship inference are not targeted at POI, thus failing to capture unique spatial characteristics that have huge effects on POI relationships. In this work we propose PRIM to tackle POI relationship inference for multiple relation types. PRIM features four novel components, including a weighted relational graph neural network, category taxonomy integration, a self-attentive spatial context extractor, and a distance-specific scoring function. Extensive experiments on two real-world datasets show that PRIM achieves the best results compared to state-of-the-art baselines and it is robust against data sparsity and is applicable to unseen cases in practice.