Search

Abstract Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model’s predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet’s performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms. Scientific contribution The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible.

Abstract The prediction of potential protein–protein interactions (PPIs) is a critical step in decoding diseases and understanding cellular mechanisms. Traditional biological experiments have identified plenty of potential PPIs in recent years, but this problem is still far from being solved. Hence, there is urgent to develop computational models with good performance and high efficiency to predict potential PPIs. In this study, we propose a multi-source molecular network representation learning model (called MultiPPIs) to predict potential protein–protein interactions. Specifically, we first extract the protein sequence features according to the physicochemical properties of amino acids by utilizing the auto covariance method. Second, a multi-source association network is constructed by integrating the known associations among miRNAs, proteins, lncRNAs, drugs, and diseases. The graph representation learning method, DeepWalk, is adopted to extract the multisource association information of proteins with other biomolecules. In this way, the known protein–protein interaction pairs can be represented as a concatenation of the protein sequence and the multi-source association features of proteins. Finally, the Random Forest classifier and corresponding optimal parameters are used for training and prediction. In the results, MultiPPIs obtains an average 86.03% prediction accuracy with 82.69% sensitivity at the AUC of 93.03% under five-fold cross-validation. The experimental results indicate that MultiPPIs has a good prediction performance and provides valuable insights into the field of potential protein–protein interactions prediction. MultiPPIs is free available at https://github.com/jiboyalab/multiPPIs .

This research article outlines a study that examines the creation of a comprehensive knowledge graph specifically designed for the domain of urban agriculture. The research centers on the acquisition, synthesis, and arrangement of pertinent information from various origins in order to establish a specialized knowledge graph tailored for urban agricultural systems. The graph depicts the interrelationships and attributes of various entities, including urban farms, crops, farming methods, environmental factors, and economic elements. Moreover, this study investigates the efficacy of different graph embedding methodologies in the domain of urban agriculture. The aforementioned techniques are utilized in the context of the urban agriculture knowledge graph in order to extract significant representations of entities and their relationships. The primary objective of the experimental study is to investigate and reveal semantic relationships, patterns, and predictions that have the potential to improve decision-making processes and optimize practices in the field of urban agriculture. The results of this study make a significant contribution to the existing body of knowledge in the area of urban agriculture. Additionally, they offer valuable insights into the potential uses of graph embedding techniques within this field.

Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model's predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet's performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms. Scientific contribution The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) have shown significant success in graph representation learning. However, the performance of existing GNNs degrades seriously when their layers deepen due to the over-smoothing issue. The node embedding incline converges to a certain value when GNNs repeat, aggregating the representations of the receptive field. The main reason for over-smoothing is that the receptive field of each node tends to be similar as the layers increase, which leads to different nodes aggregating similar information. To solve this problem, we propose an adaptive multi-channel deep graph neural network (AMD-GNN) to adaptively and symmetrically aggregate information from the deep receptive field. The proposed model ensures that the receptive field of each node in the deep layer is different so that the node representations are distinguishable. The experimental results demonstrate that AMD-GNN achieves state-of-the-art performance on node classification tasks with deep models. [ABSTRACT FROM AUTHOR]

Sound classification plays a crucial role in enhancing the interpretation, analysis, and use of acoustic data, leading to a wide range of practical applications, of which environmental sound analysis is one of the most important. In this paper, we explore the representation of audio data as graphs in the context of sound classification. We propose a methodology that leverages pre-trained audio models to extract deep features from audio files, which are then employed as node information to build graphs. Subsequently, we train various graph neural networks (GNNs), specifically graph convolutional networks (GCNs), GraphSAGE, and graph attention networks (GATs), to solve multi-class audio classification problems. Our findings underscore the effectiveness of employing graphs to represent audio data. Moreover, they highlight the competitive performance of GNNs in sound classification endeavors, with the GAT model emerging as the top performer, achieving a mean accuracy of 83% in classifying environmental sounds and 91% in identifying the land cover of a site based on its audio recording. In conclusion, this study provides novel insights into the potential of graph representation learning techniques for analyzing audio data. [ABSTRACT FROM AUTHOR]

The prediction of potential protein–protein interactions (PPIs) is a critical step in decoding diseases and understanding cellular mechanisms. Traditional biological experiments have identified plenty of potential PPIs in recent years, but this problem is still far from being solved. Hence, there is urgent to develop computational models with good performance and high efficiency to predict potential PPIs. In this study, we propose a multi-source molecular network representation learning model (called MultiPPIs) to predict potential protein–protein interactions. Specifically, we first extract the protein sequence features according to the physicochemical properties of amino acids by utilizing the auto covariance method. Second, a multi-source association network is constructed by integrating the known associations among miRNAs, proteins, lncRNAs, drugs, and diseases. The graph representation learning method, DeepWalk, is adopted to extract the multisource association information of proteins with other biomolecules. In this way, the known protein–protein interaction pairs can be represented as a concatenation of the protein sequence and the multi-source association features of proteins. Finally, the Random Forest classifier and corresponding optimal parameters are used for training and prediction. In the results, MultiPPIs obtains an average 86.03% prediction accuracy with 82.69% sensitivity at the AUC of 93.03% under five-fold cross-validation. The experimental results indicate that MultiPPIs has a good prediction performance and provides valuable insights into the field of potential protein–protein interactions prediction. MultiPPIs is free available at . [ABSTRACT FROM AUTHOR]

Graph embedding plays an important role in the analysis and study of typical non-Euclidean data, such as graphs. Graph embedding aims to transform complex graph structures into vector representations for further machine learning or data mining tasks. It helps capture relationships and similarities between nodes, providing better representations for various tasks on graphs. Different orders of neighbors have different impacts on the generation of node embedding vectors. Therefore, this paper proposes a multi-order adjacency view encoder to fuse the feature information of neighbors at different orders. We generate different node views for different orders of neighbor information, consider different orders of neighbor information through different views, and then use attention mechanisms to integrate node embeddings from different views. Finally, we evaluate the effectiveness of our model through downstream tasks on the graph. Experimental results demonstrate that our model achieves improvements in attributed graph clustering and link prediction tasks compared to existing methods, indicating that the generated embedding representations have higher expressiveness. [ABSTRACT FROM AUTHOR]

Heterogeneous graph representation learning has strong expressiveness when dealing with large-scale relational graph data, and its purpose is to effectively represent the semantic information and heterogeneous structure information of nodes in the graph. Current methods typically use shallow models to embed semantic information on low-order neighbor nodes in the graph, which prevents the complete retention of higher-order semantic feature information. To address this issue, this paper proposes a heterogeneous graph network for higher-order semantic enhancement called HHSE. Specifically, our model uses the identity mapping mechanism of residual attention at the node feature level to enhance the information representation of nodes in the hidden layer, and then utilizes two aggregation strategies to improve the retention of high-order semantic information. The semantic feature level aims to learn the semantic information of nodes in various meta path subgraphs. Extensive experiments on node classification and node clustering on three real-existing datasets show that the proposed approach makes practical improvements compared to the state-of-the-art methods. Besides, our method is applicable to large-scale heterogeneous graph representation learning. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) have many variants for graph representation learning. Several works introduce PageRank into GNNs to improve its neighborhood aggregation capabilities. However, these methods leverage the general PageRank to perform complex neighborhood aggregation to obtain the final feature representation, which leads to high computational cost and oversmoothing. In this paper, we propose simple hierarchical PageRank graph neural networks (SHP-GNNs), which first utilize the simple PageRank to aggregate different neighborhood ranges of each node and then leverage a jumping architecture to combine these aggregated features to enable hierarchical structure-aware representation. In this case, first, the simple PageRank turns the neighborhood aggregation process to no-learning, thereby reducing the computational complexity of the model. Then, the jumping structure combines the aggregation features of each node's different hierarchy (neighborhood range) to learn more informative feature representation. Finally, the successful combination of the above methods alleviates the oversmoothing problem of deep GNNs. Our experimental evaluation demonstrates that SHP-GNNs achieve or match state-of-the-art results in node classification tasks, text classification tasks, and community prediction tasks. Moreover, since SHP-GNNs' neighborhood aggregation is a no-learning process, SHP-GNNs are more suitable for node clustering tasks. [ABSTRACT FROM AUTHOR]

Variational Graph Autoencoders (VAGE) emerged as powerful graph representation learning methods with promising performance on graph analysis tasks. However, existing methods typically rely on Graph Convolutional Networks (GCN) to encode the attributes and topology of the original graph. This strategy makes it difficult to fully learn high-order neighborhood information, which weakens the capacity to learn higher-quality representations. To address the above issues, we propose the Multi-order Variational Graph Autoencoders (MoVGAE) with co-learning of first-order and high-order neighborhoods. GCN and Multi-order Graph Convolutional Networks (MoGCN) are utilized to generate the mean and variance for the variational autoencoders. Then, MoVGAE uses the mean and variance to calculate node representations. Specifically, this approach comprehensively encodes first-order and high-order information in the graph data. Finally, the decoder reconstructs the adjacency matrix by performing the inner product of the representations. Experiments with the proposed method were conducted on node classification, node clustering, and link prediction tasks on real-world graph datasets. The results demonstrate that MoVGAE achieves state-of-the-art performance compared to other baselines in various tasks. Furthermore, the robustness analysis verifies that MoVGAE has obvious advantages in the processes of graph data with insufficient attributes and topology.

Graph neural network (GNN) is a formidable deep learning framework that enables the analysis and modeling of intricate relationships present in data structured as graphs. In recent years, a burgeoning interest has arisen in exploiting the latent capabilities of GNN for healthcare-based applications, capitalizing on their aptitude for modeling complex relationships and unearthing profound insights from graph-structured data. However, to the best of our knowledge, no study has systemically reviewed the GNN studies conducted in the healthcare domain. This study has furnished an all-encompassing and erudite overview of the prevailing cutting-edge research on GNN in healthcare. Through analysis and assimilation of studies, current research trends, recurrent challenges, and promising future opportunities in GNN for healthcare applications have been identified. China emerged as the leading country to conduct GNN-based studies in the healthcare domain, followed by the USA, UK, and Turkey. Among various aspects of healthcare, disease prediction and drug discovery emerge as the most prominent areas of focus for GNN application, indicating the potential of GNN for advancing diagnostic and therapeutic approaches. This study proposed research questions regarding diverse aspects of GNN in the healthcare domain and addressed them through an in-depth analysis. This study can provide practitioners and researchers with profound insights into the current landscape of GNN applications in healthcare and can guide healthcare institutes, researchers, and governments by demonstrating the ways in which GNN can contribute to the development of effective and efficient healthcare systems.

Abstract Most human activities require collaborations within and across formal or informal teams. Our understanding of how the collaborative efforts spent by teams relate to their performance is still a matter of debate. Teamwork results in a highly interconnected ecosystem of potentially overlapping components where tasks are performed in interaction with team members and across other teams. To tackle this problem, we propose a graph neural network model to predict a team’s performance while identifying the drivers determining such outcome. In particular, the model is based on three architectural channels: topological, centrality, and contextual, which capture different factors potentially shaping teams’ success. We endow the model with two attention mechanisms to boost model performance and allow interpretability. A first mechanism allows pinpointing key members inside the team. A second mechanism allows us to quantify the contributions of the three driver effects in determining the outcome performance. We test model performance on various domains, outperforming most classical and neural baselines. Moreover, we include synthetic datasets designed to validate how the model disentangles the intended properties on which our model vastly outperforms baselines.

Abstract Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently. However, there are still two challenges. First, most of the real‐word system are multiple relations, where entities are linked by different types of relations, and each relation is a view of the graph network. Second, the rich multi‐scale information (structure‐level and feature‐level) of the graph network can be seen as self‐supervised signals, which are not fully exploited. A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale (named CoLM 2 S) information is presented in this study. It mainly contains two components: intra‐relation contrast learning and inter‐relation contrastive learning. Specifically, the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information (CoLMS) framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level self‐supervised signals is introduced first. The structure‐level information includes the edge structure and sub‐graph structure, and the feature‐level information represents the output of different graph convolutional layer. Second, according to the consensus assumption among inter‐relations, the CoLM2S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding. The proposed method can fully distil the graph information. Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods, and it outperforms existing competitive baselines.

Discovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing sequential and global representation due to their reliance on prior knowledge or feature engineering. The current models based on deep learning focus on extracting implicit behavioral characteristics from combat process data, overlooking the embedded martial knowledge within the recognition of combat intentions. In this work, we fill the above challenge by proposing a dual fusion pipeline introducing graph representation learning into sequence learning to construct tactical behavior sequence graphs expressing implicit martial knowledge, named TBGCN. Specifically, the TBGCN utilizes graph representation learning to represent prior knowledge by building a graph to induce deep learning paradigms, and sequence learning finds the hidden representation from the target's serialized data. Then, we employ a fusion module to merge two such representations. The significance of integrating graphs with deep learning lies in using the artificial experience of implicit graph structure guiding adaptive learning, which can improve representation ability and model generalization. Extensive experimental results demonstrate that the proposed TBGCN can effectively discover tactical knowledge and significantly outperform the traditional and deep learning methods. [ABSTRACT FROM AUTHOR]

Maximal frequent subgraph mining (MFSM) is the task of mining only maximal frequent subgraphs, i.e., subgraphs that are not a part of other frequent subgraphs. Although many intelligent systems require MFSM, MFSM is challenging compared to frequent subgraph mining (FSM), as maximal frequent subgraphs lie in the middle of graph lattice, and FSM algorithms must explore an exponential space and an NP-hard subroutine of frequency counting. Different from prior research, which primarily focused on optimal solutions, we introduce pmMine, a progressive graph neural framework designed for MFSM in a single large graph to attain an approximate solution. The framework combines isomorphic graph embedding, non-parametric partitioning, and an efficiently top-down pattern searching strategy. The critical insight that makes pmMine work is to define the concepts of rooted subgraph and isomorphic graph embedding, in which the costly isomorphism subroutine can be efficiently performed using similarity estimation in embedding space. In addition, pmMine returns the patterns identified during the mining process in a progressive manner. We validate the efficiency and effectiveness of our technique through extensive experiments on a variety of datasets spanning various domains. [ABSTRACT FROM AUTHOR]

Graph representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate graph representation vectors that capture the structure and features of large graphs accurately. This is especially important because the quality of the graph representation vectors will affect the performance of these vectors in downstream tasks such as node classification, link prediction and anomaly detection. Many techniques have been proposed for generating effective graph representation vectors, which generally fall into two categories: traditional graph embedding methods and graph neural network (GNN)–based methods. These methods can be applied to both static and dynamic graphs. A static graph is a single fixed graph, whereas a dynamic graph evolves over time and its nodes and edges can be added or deleted from the graph. In this survey, we review the graph-embedding methods in both traditional and GNN-based categories for both static and dynamic graphs and include the recent papers published until the time of submission. In addition, we summarize a number of limitations of GNNs and the proposed solutions to these limitations. Such a summary has not been provided in previous surveys. Finally, we explore some open and ongoing research directions for future work. [ABSTRACT FROM AUTHOR]

Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. To deal with the performance degradation issue when HGNNs become deep, researchers combine metapaths into HGNNs to associate nodes closely related in semantics but far apart in the graph. However, existing metapath-based models suffer from either information loss or high computation costs. To address these problems, we present a novel Metapath Context Convolution-based Heterogeneous Graph Neural Network (MECCH). MECCH leverages metapath contexts , a new kind of graph structure that facilitates lossless node information aggregation while avoiding any redundancy. Specifically, MECCH applies three novel components after feature preprocessing to extract comprehensive information from the input graph efficiently: (1) metapath context construction, (2) metapath context encoder, and (3) convolutional metapath fusion. Experiments on five real-world heterogeneous graph datasets for node classification and link prediction show that MECCH achieves superior prediction accuracy compared with state-of-the-art baselines with improved computational efficiency. The code is available at https://github.com/cynricfu/MECCH. • Unified a framework for metapath-based HGNNs and analyzed their limitations. • Introduced metapath contexts for lossless and efficient node information aggregation. • Proposed MECCH that leverages metapath contexts with better efficacy and efficiency. [ABSTRACT FROM AUTHOR]

The adaptive fusion module with an attention mechanism functions by employing a dual-channel graph convolutional network to aggregate neighborhood information. The resulting embeddings are then utilized to calculate interaction terms, thereby incorporating additional information. To enhance the relevance of fusion information, an adaptive fusion module with an attention mechanism is constructed. This module selectively combines the neighborhood aggregation and interaction terms, prioritizing the most pertinent information. Through this adaptive fusion process, the algorithm effectively captures both neighborhood features and other nonlinear information, leading to improved overall performance. Neighborhood Aggregation Interaction Graph Convolutional Network Adaptive Fusion (NAIGCNAF) is a graph representation learning algorithm designed to obtain low-dimensional node representations while preserving graph properties. It addresses the limitations of existing algorithms, which tend to focus solely on aggregating neighborhood features and overlook other nonlinear information. NAIGCNAF utilizes a dual-channel graph convolutional network for neighborhood aggregation and calculates interaction terms based on the resulting embeddings. Additionally, it incorporates an adaptive fusion module with an attention mechanism to enhance the relevance of fusion information. Extensive evaluations on three citation datasets demonstrate that NAIGCNAF outperforms other algorithms such as GCN, Neighborhood Aggregation, and AIR-GCN. NAIGCNAF achieves notable improvements in classification accuracy, ranging from 1.0 to 1.6 percentage points on the Cora dataset, 1.1 to 2.4 percentage points on the Citeseer dataset, and 0.3 to 0.9 percentage points on the Pubmed dataset. Moreover, in visualization tasks, NAIGCNAF exhibits clearer boundaries and stronger aggregation within clusters, enhancing its effectiveness. Additionally, the algorithm showcases faster convergence rates and smoother accuracy curves, further emphasizing its ability to improve benchmark algorithm performance. [ABSTRACT FROM AUTHOR]

The stability of the gut microenvironment is inextricably linked to human health, with the onset of many diseases accompanied by dysbiosis of the gut microbiota. It has been reported that there are differences in the microbial community composition between patients and healthy individuals, and many microbes are considered potential biomarkers. Accurately identifying these biomarkers can lead to more precise and reliable clinical decision-making. To improve the accuracy of microbial biomarker identification, this study introduces WSGMB, a computational framework that uses the relative abundance of microbial taxa and health status as inputs. This method has two main contributions: (1) viewing the microbial co-occurrence network as a weighted signed graph and applying graph convolutional neural network techniques for graph classification; (2) designing a new architecture to compute the role transitions of each microbial taxon between health and disease networks, thereby identifying disease-related microbial biomarkers. The weighted signed graph neural network enhances the quality of graph embeddings; quantifying the importance of microbes in different co-occurrence networks better identifies those microbes critical to health. Microbes are ranked according to their importance change scores, and when this score exceeds a set threshold, the microbe is considered a biomarker. This framework's identification performance is validated by comparing the biomarkers identified by WSGMB with actual microbial biomarkers associated with specific diseases from public literature databases. The study tests the proposed computational framework using actual microbial community data from colorectal cancer and Crohn's disease samples. It compares it with the most advanced microbial biomarker identification methods. The results show that the WSGMB method outperforms similar approaches in the accuracy of microbial biomarker identification. [ABSTRACT FROM AUTHOR]

Analyzing and modeling the implicit semantic relationships in data sources is the key to achieving integration and sharing of heterogeneous data information. However, manual modeling of data semantics is a laborious and error-prone task that demands significant human effort and expertise. The paper proposes a novel explainable representation learning-based method that adopts an attention-based table-graph cross-modal retrieval model as a rating function during incremental search for automatic semantic modeling. Our supervised model utilizes the graph representation learning technique to extract latent semantics from data and aims to retrieve the most reliable semantic model for structured data sources. Experimental results demonstrate the effectiveness and robustness of our method. • A novel supervised table-graph cross-modal retrieval model for automatic semantic modeling. • An explainable representation learning method combining graph representation learning with an incremental search algorithm. • An attention mechanism and iterative matching method to learn fine-grained semantic matches between different modalities. • The experimental results using two different semantic labelers validate the effectiveness and robustness of our method. • The cross-modal retrieval-based method outperforms the previous best method in terms of precision, recall, and f1-score. [ABSTRACT FROM AUTHOR]

Subjectivity and uncertainty of risk assessment (RA) procedures can be improved by replacing guesswork with data-driven approaches such as machine learning (ML). Although a plethora of ML prediction techniques have been introduced to improve the reliability of RA procedures, the utilization of ML-based recommendation systems that can leverage data from multiple aspects has remained unexplored. In this study, a novel RA recommendation system (RARS) was developed to achieve more reliable, objective, and inclusive safety decisions that can prioritize hazard items and formulate related risky scenarios. To this end, a semisupervised graph representation learning framework, node2vec, was utilized to receive semantic and dependency information from safety records to recommend the components of potential accident scenarios (hazards, hazardous cases, dangerous activities, and risky behaviors) based on the given decision objective. The RARS's ability to provide flexible and user-oriented safety recommendations was explored on a real-life construction accident data set. This allows construction safety practitioners to dynamically evaluate possible risky scenarios with details regarding different influential risk factors and accordingly devise more reliable site safety strategies and relevant policies. The proposed RARS, through its adoption of the graph representation learning-based recommendation model, has the potential to advance hazard identification and risky scenario formulation during the risk analysis and evaluation stages for three reasons: first, a relation-aware representation data set is structured while assigning each hazard item to the project, related safety features, and different construction occupations; second, it allows flexible configuration of the system input based on different decision objectives by the construction professionals; and third, it provides data-driven recommendations by learning the relationship between the characteristics of different safety data collected across various projects while considering the project similarities in terms of the shared safety attributes. The proposed RARS can identify patterns and relationships in construction safety data sets to generate suggestions and recommendations, even in the absence of explicit labels or outcomes. RARS can suggest relevant hazards, hazardous cases, dangerous activities, and risky behavior items, considering the safety features shared among different projects and construction occupations. This facilitates its constant utilization during the procedure of formulating different safety scenarios that are often performed based on experience-driven guess works, while there may be incomplete or missing data, which is a common occurrence in RA procedures. [ABSTRACT FROM AUTHOR]

Massive multiplayer online role-playing games (MMORPG) have been becoming one of the most popular and exciting online games. In recent years, a cheating phenomenon called real money trading (RMT) has arisen and damaged the fantasy world in many ways. RMT is the sale of in-game items, currency, or even characters to earn real money, breaking the balance of the game economy ecosystem and damaging the game experience. Therefore, some studies have emerged to address the problem of RMT detection. However, they cannot well handle the label uncertainty problem in practice, where there are only labeled RMT samples (positive samples) and unlabeled samples, which could either be RMT samples or normal transactions (negative samples). Meanwhile, the trading relationship between RMTers is modeled in a simple way, leading to some normal transactions being falsely classified as RMT. In this article, we propose PU-Detector, a novel framework based on PU learning (learning from positive and unlabeled data) for RMT detection, considering the fact that there are only labeled RMT samples and other unlabeled transactions. We first automatically estimate the likelihood of one transaction being RMT by developing an improved PU learning method and proposing an assessment rule. Sequentially, we use the estimated likelihood as edge weight to construct a trading graph to learn trader representation. Then, with the trader representations and basic trading features, we detect RMT samples by the improved PU learning method. PU-Detector is evaluated on a large-scale real world dataset consisting of 33,809,956 transaction logs generated by 43,217 unique players. Compared with other approaches, it achieves the state-of-the-art performance and demonstrates its advantages in detecting underlying RMT samples. [ABSTRACT FROM AUTHOR]

Contrastive learning is an effective unsupervised method in graph representation learning. The key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle. Recently, the data-augmentation-based contrastive learning method has advanced to show great power in the visual domain, and some works have extended this method from images to graphs. However, unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and it is much harder to provide high-quality contrastive samples, which leaves much space for improvement. In this work, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ArieL), to extract informative contrastive samples within reasonable constraints. We develop a new technique called information regularization for stable training and use subgraph sampling for scalability. We generalize our method from node-level contrastive learning to the graph level by treating each graph instance as a super-node. ArieL consistently outperforms the current graph contrastive learning methods for both node-level and graph-level classification tasks on real-world datasets. We further demonstrate that ArieL is more robust in the face of adversarial attacks. [ABSTRACT FROM AUTHOR]

Graph pooling refers to the operation that maps a set of node representations into a compact form for graph-level representation learning. However, existing graph pooling methods are limited by the power of the Weisfeiler–Lehman (WL) test in the performance of graph discrimination. In addition, these methods often suffer from hard adaptability to hyper-parameters and training instability. To address these issues, we propose Hi-PART, a simple yet effective graph neural network (GNN) framework with Hierarchical Partition Tree (HPT). In HPT, each layer is a partition of the graph with different levels of granularities that are going toward a finer grain from top to bottom. Such an exquisite structure allows us to quantify the graph structure information contained in HPT with the aid of structural information theory. Algorithmically, by employing GNNs to summarize node features into the graph feature based on HPT's hierarchical structure, Hi-PART is able to adequately leverage the graph structure information and provably goes beyond the power of the WL test. Due to the separation of HPT optimization from graph representation learning, Hi-PART involves the height of HPT as the only extra hyper-parameter and enjoys higher training stability. Empirical results on graph classification benchmarks validate the superior expressive power and generalization ability of Hi-PART compared with state-of-the-art graph pooling approaches. [ABSTRACT FROM AUTHOR]

Graph Neural Networks (GNNs) play a significant role in tasks related to homophilic graphs. Traditional GNNs, based on the assumption of homophily, employ low-pass filters for neighboring nodes to achieve information aggregation and embedding. However, in heterophilic graphs, nodes from different categories often establish connections, while nodes of the same category are located further apart in the graph topology. This characteristic poses challenges to traditional GNNs, leading to issues of "distant node modeling deficiency" and "failure of the homophily assumption". In response, this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks (SFA-HGNN), which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues. Specifically, for the first problem, we propose the "Distant Spatial Embedding Module", aiming to select and aggregate distant nodes through high-order random walk transition probabilities to enhance modeling capabilities. For the second issue, we design the "Proximal Frequency Domain Embedding Module", constructing adaptive filters to separate high and low-frequency signals of nodes, and introduce frequency-domain guided attention mechanisms to fuse the relevant information, thereby reducing the noise introduced by the failure of the homophily assumption. We deploy the SFA-HGNN on six publicly available heterophilic networks, achieving state-of-the-art results in four of them. Furthermore, we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation, demonstrating a positive correlation between "node structural similarity", "node attribute vector similarity", and "node homophily" in heterophilic networks. [ABSTRACT FROM AUTHOR]

Self-supervised graph representation learning has been widely used in many intelligent applications since labeled information can hardly be found in these data environments. Currently, masking and reconstruction-based (MR-based) methods lead the state-of-the-art records in the self-supervised graph representation field. However, existing MR-based methods did not fully consider both the deep-level node and structure information which might decrease the final performance of the graph representation. To this end, this paper proposes a node and edge dual-masked self-supervised graph representation model to consider both node and structure information. First, a dual masking model is proposed to perform node masking and edge masking on the original graph at the same time to generate two masking graphs. Second, a graph encoder is designed to encode the two generated masking graphs. Then, two reconstruction decoders are designed to reconstruct the nodes and edges according to the masking graphs. At last, the reconstructed nodes and edges are compared with the original nodes and edges to calculate the loss values without using the labeled information. The proposed method is validated on a total of 14 datasets for graph node classification tasks and graph classification tasks. The experimental results show that the method is effective in self-supervised graph representation. The code is available at: https://github.com/TangPeng0627/Node-and-Edge-Dual-Mask. [ABSTRACT FROM AUTHOR]

In the detection of slipping anomalies in viscoelastic sandwich cylindrical structures (VSCS), conventional methods may encounter challenges due to the extremely rare and weak nature of slipping signals. This study focuses on normal signals and introduces unsupervised graph representation learning (UGRL) with discriminative embedding similarity for VSCS's detection. UGRL involves data preprocessing, model embedding, and matrix reconstructing. Association graphs are constructed based on sample similarities for yielding adjacency and attribute matrices. Subsequently, the matrices undergo embedding and reconstruction via various network modules to enhance graph data characterization. Detection indicators are derived by calculating embedding similarities and reconstruction errors, and thresholds are constructed using these indicators to enable efficient anomaly detection. The experiments in VSCS slipping dataset effectively indicate the superiority of the proposed method. • Unsupervised graph anomaly detection is proposed for viscoelastic sandwich cylindrical structures. • Graphs are constructed to capture the attribute characteristics and similarity correlations within normal samples. • Graph representation learning captures information among nodes and enhances the expression of graph data. • Reconstruction errors and embedding similarity errors are integrated to strengthen the anomaly detection ability. [ABSTRACT FROM AUTHOR]

Abstract Link prediction is a widely adopted method for extracting valuable data insights from graphs, primarily aimed at predicting interactions between two nodes. However, there are not only pairwise interactions but also multivariate interactions in real life. For example, reactions between multiple proteins, multiple compounds, and multiple metabolites cannot be mined effectively using link prediction. A hypergraph is a higher-order network composed of nodes and hyperedges, where hyperedges can be composed of multiple nodes, and can be used to depict multivariate interactions. The interactions between multiple nodes can be predicted by hyperlink prediction methods. Since hyperlink prediction requires predicting the interactions between multiple nodes, it makes the study of hyperlink prediction much more complicated than that of other complex networks, thus resulting in relatively limited attention being devoted to this field. The existing hyperlink prediction can only predict potential hyperlinks in uniform hypergraphs, or need to predict hyperlinks based on the candidate hyperlink sets, or only study hyperlink prediction for undirected hypergraphs. Therefore, a hyperlink prediction framework for predicting multivariate interactions based on graph representation learning is proposed to solve the above problems, and then the framework is extended to directed hyperlink prediction (e.g., directed metabolic reaction networks). Furthermore, any size of hyperedges can be predicted by the proposed hyperlink prediction algorithm framework, whose performance is not affected by the number of nodes or the number of hyperedges. Finally, the proposed framework is applied to both the biological metabolic reaction network and the organic chemical reaction network, and experimental analysis has demonstrated that the hyperlinks can be predicted efficiently by the proposed hyperlink prediction framework with relatively low time complexity, and the prediction performance has been improved by up to 40% compared with the baselines.

Portfolio optimization is one of the essential fields of focus in finance. There has been an increasing demand for novel computational methods in this area to compute portfolios with better returns and lower risks in recent years. We present a novel computational method called Representation Portfolio Selection by redefining the distance matrix of financial assets using Representation Learning and Clustering algorithms for portfolio selection to increase diversification. RPS proposes a heuristic for getting closer to the optimal subset of assets. Using empirical results in this paper, we demonstrate that widely used portfolio optimization algorithms, such as Mean-Variance Optimization, Critical Line Algorithm, and Hierarchical Risk Parity can benefit from our asset subset selection.

Graph contrastive learning has made remarkable achievements in the self-supervised representation learning of graph-structured data. By employing perturbation function (i.e., perturbation on the nodes or edges of graph), most graph contrastive learning methods construct contrastive samples on the original graph. However, the perturbation-based data augmentation methods randomly change the inherent information (e.g., attributes or structures) of the graph. Therefore, after nodes embedding on the perturbed graph, we cannot guarantee the validity of the contrastive samples as well as the learned performance of graph contrastive learning. To this end, in this article, we propose a novel generation-based multi-view contrastive learning framework (GMVC) for self-supervised graph representation learning, which generates the contrastive samples based on our generator rather than perturbation function. Specifically, after nodes embedding on the original graph we first employ random walk in the neighborhood to develop multiple relevant node sequences for each anchor node. We then utilize the transformer to generate the representations of relevant contrastive samples of anchor node based on the features and structures of the sampled node sequences. Finally, by maximizing the consistency between the anchor view and the generated views, we force the model to effectively encode graph information into nodes embeddings. We perform extensive experiments of node classification and link prediction tasks on eight benchmark datasets, which verify the effectiveness of our generation-based multi-view graph contrastive learning method. [ABSTRACT FROM AUTHOR]

Abstract The development of the Internet and big data has led to the emergence of graphs as an important data representation structure in various real-world scenarios. However, as data size increases, computational complexity and memory requirements pose significant challenges for graph embedding. To address this challenge, this paper proposes a multilevel embedding refinement framework (MERIT) based on large-scale graphs, using spectral distance-constrained graph coarsening algorithms and an improved graph convolutional neural network model that addresses the over-smoothing problem by incorporating initial values and identity mapping. Experimental results on large-scale datasets demonstrate the effectiveness of MERIT, with an average AUROC score 8% higher than other baseline methods. Moreover, in a node classification task on a large-scale graph with 126,825 nodes and 22,412,658 edges, the framework improves embedding quality while enhancing the runtime by 25 times. The experimental findings highlight the superior efficiency and accuracy of the proposed approach compared to other graph embedding methods.

Abstract Patient similarity search is an essential task in healthcare. Recent studies adopted electronic health records (EHRs) to learn patient representations for measuring the clinical similarities. These methods outperformed traditional methods, by capturing more information from various sources consisting of multi-modal EHRs, external knowledge and correlations among medical concepts. They often concerned certain type of data without taking full advantage of various information. We propose a graph representation learning framework, denoted by One-Size-Fits-Three (OSFT), that takes into account fusion-attention, neighbor-attention and global-attention from three types of information. Extensive experiments are conducted on two real datasets of MIMIC-III and MIMIC-IV, and the results verified the effectiveness and generality of our framework. When compared with baselines on patient similarity search, our framework achieved good effectiveness and comparative efficiency. The results provide new insights about whether the use of various information can better measure the patient similarity. The source codes are available at https://github.com/emmali808/ADDS/tree/master/EHRDeepHelper .

Abstract In recent years, a surge of criminal activities with cross-cryptocurrency trades have emerged in Ethereum, the second-largest public blockchain platform. Most of the existing anomaly detection methods utilize the traditional machine learning with feature engineering or graph representation learning technique to capture the information in transaction network. However, these methods either ignore the timestamp information and the transaction flow direction information in transaction network or only consider single transaction network, the cross-cryptocurrency trading patterns in Ethereum are usually ignored. In this paper, we introduce a Multi-layer Temporal Transaction Anomaly Detection (MT $$^2$$ 2 AD) model in Ethereum network with graph neural network. Specifically, for a given Ethereum token transaction network, we first extract its initial features including the structure subgraph and edge’s feature. Then, we model the temporal information in subgraph as a series of network snapshots according to the timestamp on each edge and time window. To capture the cross-cryptocurrency trading patterns, we combine the snapshots from multiple token transactions at a given timestamp, and we consider it as a new combined graph. We further use the graph convolution encoder with attention mechanism and pooling operation on this new graph to obtain the graph-level embedding, and we transform the anomaly detection on dynamic multi-layer Ethereum transaction networks as a graph classification task with these graph-level embeddings. MT $$^2$$ 2 AD can integrate the transaction structure feature, edge’s feature and cross-cryptocurrency trading patterns into a framework to perform the anomaly detection with graph neural networks. Experiments on three real-world multi-layer transaction networks show that the proposed MT $$^2$$ 2 AD (0.8789 Precision, 0.9375 Recall, 0.4987 FbMacro and 0.9351 FbWeighted) can achieve the best performance on most evaluation metrics in comparison with some competing approaches, and the effectiveness in consideration of multiple tokens is also demonstrated.

Abstract Graph representation learning has made significant strides in various fields, including sociology and biology, in recent years. However, the majority of research has focused on static graphs, neglecting the temporality and continuity of edges in dynamic graphs. Furthermore, dynamic data are vulnerable to various security threats, such as data privacy breaches and confidentiality attacks. To tackle this issue, the present paper proposes a data security detection method based on a continuous-time graph embedding framework (CTDGE). The framework models temporal dependencies and embeds data using a graph representation learning method. A machine learning algorithm is then employed to classify and predict the embedded data to detect if it is secure or not. Experimental results show that this method performs well in data security detection, surpassing several dynamic graph embedding methods by 5% in terms of AUC metrics. Furthermore, the proposed framework outperforms other dynamic baseline methods in the node classification task of large-scale graphs containing 4321477 temporal information edges, resulting in a 10% improvement in the F1 score metric. The framework is also robust and scalable for application in various data security domains. This work is important for promoting the use of continuous-time graph embedding framework in the field of data security.