Graph Representation Research Articles

KGFabric: A Scalable Knowledge Graph Warehouse for Enterprise Data Interconnection

Based on the diversified application scenarios at Ant Group, we built the Ant Knowledge Graph Platform (AKGP). It has constructed numerous domain-specific knowledge graphs related to merchants, companies, accounts, products, and more. AKGP manages trillions of structured knowledge graphs, serving search, recommendation, risk control and other businesses. However, as the demand increasing for various workloads such as graph pattern matching, graph representation learning, and cross-domain knowledge reuse, the existing warehouse systems based on relational DBMS or graph databases are unable to meet the requirements. To address these issues, we propose KGFabric, an industrial-scale knowledge graph management system built on the distributed file system (DFS). KGFabric offers a nearline knowledge storage engine that utilizes a Semantic-enhanced Programmable Graph (SPG) model, which is compatible with the Labeled Property Graph (LPG) model. The data is persistently stored in DFS, such as HDFS, which leverages the POSIX file system API, making it suitable for deployment in multi-cloud environment at low cost. KGFabric provides a native graph-based and hybrid storage format that can serve as a shared backend for parallel graph computing systems, significantly accelerating the analysis of multi-workload. Additionally, KGFabric includes a graph fabric framework that minimizes data duplication and guarantees data security. KGFabric is able to manage Peta-scale data and has supported graph fabric and analysis with over 100 billion relations at Ant Group. We conduct experiments on various datasets to evaluate the performance of KGFabric. Compared with popular relational DBMS and graph databases, the storage space for semantic relations is reduced by over 90%. The performance of graph fabric improves by 21× in real-world workloads. In multi-hop semantic graph analysis, KGFabric enhances performance by 100×.

Deep learning and pre-training technology for encrypted traffic classification: A comprehensive review

Network traffic classification has long been a pivotal topic in network security. In the past two decades, methods like port-based classification, deep packet inspection, and machine learning approaches have significantly progressed. Still, they are now facing reduced effectiveness due to the evolving complexity of the Internet, new encryption protocols, and advanced defense strategies. Given the problem that traditional models cannot efficiently generalize encrypted traffic, two promising technology paths are currently: deep learning and pre-training. On the one hand, deep learning-based methods effectively dissect complex network structures and unearth pivotal relational patterns. These approaches excel due to the neural networks’ robust generalization capabilities, significantly boosting the accuracy and efficiency of recognition processes. Graph representation learning stands out as the most compelling contemporary model for such intricate analysis, adeptly revealing the critical relationships within network communication structures. We emphatically introduce mainstream deep learning-based methods, and the mechanism and scenarios are also analyzed. On the other hand, recognizing that although the analysis based on large models is the trend of the field, the application is truly limited now, we underscore the importance of pre-training, which aligns with the future trajectory toward the adoption of large-scale models in encrypted traffic analysis. The pre-trained model can overcome various defects of previous models and achieve more remarkable performance through its low labeled data dependency and strong scenario adaptability. We provide a comprehensive overview of existing pre-training-based approaches from the three stages of operation: input, pre-training, fine-tuning, and comparing representative relevant work. Finally, because of the current needs and the improvement space of the existing pre-training methods in the field, we synthetically analyze the challenges and opportunities for interested researchers to explore.

Enhanced Graph Representation Convolution: Effective Inferring Gene Regulatory Network Using Graph Convolution Network with Self-Attention Graph Pooling Layer

Enhanced Graph Representation Convolution: Effective Inferring Gene Regulatory Network Using Graph Convolution Network with Self-Attention Graph Pooling Layer

Sparse Graph Representation Learning Based on Reinforcement Learning for Personalized Mild Cognitive Impairment (MCI) Diagnosis.

Resting-state functional magnetic resonance imaging (rs-fMRI) has gained attention as a reliable technique for investigating the intrinsic function patterns of the brain. It facilitates the extraction of functional connectivity networks (FCNs) that capture synchronized activity patterns among regions of interest (ROIs). Analyzing FCNs enables the identification of distinctive connectivity patterns associated with mild cognitive impairment (MCI). For MCI diagnosis, various sparse representation techniques have been introduced, including statistical- and deep learning-based methods. However, these methods face limitations due to their reliance on supervised learning schemes, which restrict the exploration necessary for probing novel solutions. To overcome such limitation, prior work has incorporated reinforcement learning (RL) to dynamically select ROIs, but effective exploration remains challenging due to the vast search space during training. To tackle this issue, in this study, we propose an advanced RL-based framework that utilizes a divide-and-conquer approach to decompose the FCN construction task into smaller sub-problems in a subject-specific manner, enabling efficient exploration under each sub-problem condition. Additionally, we leverage the learned value function to determine the sparsity level of FCNs, considering individual characteristics of FCNs. We validate the effectiveness of our proposed framework by demonstrating its superior performance in MCI diagnosis on publicly available cohort datasets.

Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective

Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective

Polynomial Representation and Degree Sequence of Graphs Resulting from Some Graph Operations

Let $G = (V(G),E(G))$ be a graph with degree sequence $\langle d_1,d_2, \cdots, d_n \rangle$, where $d_1 \ge d_2 \ge \cdots \ge d_n$. The polynomial representation of $G$ is given by $f_G(x) = \displaystyle \sum_{i=1}^n x^{d_i} = \sum_{k=1}^{\Delta(G)}a_kx^{k}$, where $a_k$ is the number of vertices of $G$ having degree $k$ for each $i = 1,2,\cdots n = \Delta(G)$. In this paper, we give the polynomial representation of the complement and line graph of a graph, the shadow graph, complementary prism, edge corona, strong product, symmetric product, and disjunction of two graphs.

A Hybrid GNN Approach for Improved Molecular Property Prediction.

The development of new drugs is a vital effort that has the potential to improve human health, well-being and life expectancy. Molecular property prediction is a crucial step in drug discovery, as it helps to identify potential therapeutic compounds. However, experimental methods for drug development can often be time-consuming and resource-intensive, with a low probability of success. To address such limitations, deep learning (DL) methods have emerged as a viable alternative due to their ability to identify high-discriminating patterns in molecular data. In particular, graph neural networks (GNNs) operate on graph-structured data to identify promising drug candidates with desirable molecular properties. These methods represent molecules as a set of node (atoms) and edge (chemical bonds) features to aggregate local information for molecular graph representation learning. Despite the availability of several GNN frameworks, each approach has its own shortcomings. Although, some GNNs may excel in certain tasks, they may not perform as well in others. In this work, we propose a hybrid approach that incorporates different graph-based methods to combine their strengths and mitigate their limitations to accurately predict molecular properties. The proposed approach consists in a multi-layered hybrid GNN architecture that integrates multiple GNN frameworks to compute graph embeddings for molecular property prediction. Furthermore, we conduct extensive experiments on multiple benchmark datasets to demonstrate that our hybrid approach significantly outperforms the state-of-the-art graph-based models. The data and code scripts to reproduce the results are available in the repository, https://github.com/pedro-quesado/HybridGNN.

Fair-RGNN: Mitigating Relational Bias on Knowledge Graphs

Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning. Although KGNN effectively models the structural information from knowledge graphs, these frameworks amplify the underlying data bias that leads to discrimination towards certain groups or individuals in resulting applications. Additionally, as existing debiasing approaches mainly focus on entity-wise bias, eliminating the multi-hop relational bias that pervasively exists in knowledge graphs remains an open question. However, it is very challenging to eliminate relational bias due to the sparsity of the paths that generate the bias and the non-linear proximity structure of knowledge graphs. To tackle the challenges, we propose Fair-KGNN, a KGNN framework that simultaneously alleviates multi-hop bias and preserves the proximity information of entity-to-relation in knowledge graphs. The proposed framework is generalizable to mitigate relational bias for all types of KGNN. Fair-KGNN is applicable to incorporate two stateof- the-art KGNN models, RGCN and CompGCN, to mitigate gender-occupation and nationality-salary bias. The experiments carried out on three benchmark knowledge graph datasets demonstrate that Fair-KGNN can effectively mitigate unfair situations during representation learning while preserving the predictive performance of KGNN models. The source code of the proposed method is available at: https://github.com/ynchuang/Mitigating-Relational-Bias-on-Knowledge-Graphs .

Health indicator construction based on normal states through FFT‐graph embedding

AbstractUnexpected faults in rotating machinery can lead to cascading disruptions of the entire work process, emphasizing the importance of early detection of performance degradation and identification of the current state. To accurately assess the health of a machine, this study introduces an FFT‐based raw vibration data preprocessing and graph representation technique, which analyses changes in frequency bands to detect early degradation trends in vibration data that may appear normal. The approach proposes a methodology that utilizes a graph convolutional autoencoder trained using only normal data to extract health indicators using the differences in the vectors as degradation progresses. This approach has the advantage of using only normal data to detect subtle performance degradation early and effectively represent health indicators accordingly.

WSSGCN: Wide Sub-stage Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have emerged as a potent tool for learning graph representations, finding applications in a plethora of real-world scenarios. Nevertheless, a significant portion of deep learning research has predominantly concentrated on enhancing model performance via the construction of deeper GCNs. Regrettably, the efficacy of training deep GCNs is marred by two fundamental weaknesses: the inadequacy of conventional methodologies in handling heterogeneous networks, and the exponential surge in model complexity as network depth increases. This, in turn, imposes constraints on their practical utility. To surmount these inherent limitations, we propose an innovative approach named the Wide Sub-stage Graph Convolutional Network (WSSGCN). Our method is an outcome of meticulous observations drawn from classical and graph convolutional networks, aimed at rectifying the constraints associated with traditional GCNs. Our strategy involves the conception of a staged convolutional network framework that mirrors the fundamental tenets of the step-by-step learning process akin to human cognition. This framework prioritizes three distinct forms of consistency: response-based, feature-based, and relationship-based. Our approach involves three tailored convolutional networks capturing node/edge, subgraph, and global features. Additionally, we introduce a novel method to expand graph width for efficient GCN training. Empirical validation on benchmarks highlights WSSGCN’s superior accuracy and faster training versus conventional GCNs. WSSGCN triumphs over traditional GCN constraints, significantly enhancing graph representation learning.

Tacking over-smoothing: Target-guide progressive dynamic graph learning for 3D skeleton-based human motion prediction

Graph Convolution Network-based (GCN-based) approaches show promising performance on 3D skeleton-based human motion prediction due to its natural graph representation and outstanding ability for spatial–temporal dependencies modeling for human motion. However, the existing GCN-based methods inherently have difficulties in designing deep GCN-based structures for human motion prediction due to the over-smoothing issue. Although the over-smoothing issue has been studied in many scenarios, few attempts focus on this problem in 3D human motion prediction tasks. Therefore, we propose a novel deep GCN architecture termed TPDGN (Target-guide Progressive Dynamic Graph Network) to solve this issue in a motion prediction context. The core of the proposed TPDGN is the progressive dynamic graph leaning block, which is developed to model the dynamic graph pattern. We claim that the key to solving the over-smoothing issue is to reduce the loss of motion features and boost graph representations. Accordingly, we further explore the progressive learning mode by the specific target guidance for the motion prediction task, which aims at learning rich motion dependencies to tackle over-smoothing. Empirical results show that our approach could improve the over-smoothing issue, achieving state-of-the-art results on three public datasets. The codes is available at https://github.com/1111szu/TPDGN.

IS-GNN: Graph neural network enhanced by aggregating influential and structurally similar nodes

Nowadays, it has been demonstrated that graph neural networks (GNNs) are a powerful tool for graph representation learning. However, most GNN models are shallow ones because stacking more layers may cause the over-smoothing problem. In addition, conventional neighborhood aggregation GNNs have an implicit homophily assumption, leading to poor performance when dealing with networks with heterophily. To address the aforementioned issues, we present a new GNN model, called IS-GNN, to effectively enhance the representation quality of nodes in general networks. IS-GNN learns the representation of each node using three aspects of information: local structural information from its neighborhood, global topological information from influential nodes, and homophilous information from its structurally similar nodes. Consequently, the representations of nodes are more powerful and discriminative. The effectiveness of IS-GNN is validated on both homophilous and heterophilous networks. The experimental results of semi-supervised node classification manifest that the accuracy of IS-GNN is superior to that of baselines.

Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation.

Graph Neural Networks (GNNs) play a pivotal role in learning representations of brain networks for estimating brain age. However, the over-squashing impedes interactions between long-range nodes, hindering the ability of message-passing mechanism-based GNNs to learn the topological structure of brain networks. Graph rewiring methods and curvature GNNs have been proposed to alleviate over-squashing. However, most graph rewiring methods overlook node features and curvature GNNs neglect the geometric properties of signed curvature. In this study, a Signed Curvature GNN (SCGNN) was proposed to rewire the graph based on node features and curvature, and learn the representation of signed curvature. First, a Mutual Information Ollivier-Ricci Flow (MORF) was proposed to add connections in the neighborhood of edge with the minimal negative curvature based on the maximum mutual information between node features, improving the efficiency of information interaction between nodes. Then, a Signed Curvature Convolution (SCC) was proposed to aggregate node features based on positive and negative curvature, facilitating the model's ability to capture the complex topological structures of brain networks. Additionally, an Ollivier-Ricci Gradient Pooling (ORG-Pooling) was proposed to select the key nodes and topology structures by curvature gradient and attention mechanism, accurately obtaining the global representation for brain age estimation. Experiments conducted on six public datasets with structural magnetic resonance imaging (sMRI), spanning ages from 18 to 91 years, validate that our method achieves promising performance compared with existing methods. Furthermore, we employed the gaps between brain age and chronological age for identifying Alzheimer's Disease (AD), yielding the best classification performance.

Global-local aware Heterogeneous Graph Contrastive Learning for multifaceted association prediction in miRNA-gene-disease networks.

Unraveling the intricate network of associations among microRNAs (miRNAs), genes, and diseases is pivotal for deciphering molecular mechanisms, refining disease diagnosis, and crafting targeted therapies. Computational strategies, leveraging link prediction within biological graphs, present a cost-efficient alternative to high-cost empirical assays. However, while plenty of methods excel at predicting specific associations, such as miRNA-disease associations (MDAs), miRNA-target interactions (MTIs), and disease-gene associations (DGAs), a holistic approach harnessing diverse data sources for multifaceted association prediction remains largely unexplored. The limited availability of high-quality data, as vitro experiments to comprehensively confirm associations are often expensive and time-consuming, results in a sparse and noisy heterogeneous graph, hindering an accurate prediction of these complex associations. To address this challenge, we propose a novel framework called Global-local aware Heterogeneous Graph Contrastive Learning (GlaHGCL). GlaHGCL combines global and local contrastive learning to improve node embeddings in the heterogeneous graph. In particular, global contrastive learning enhances the robustness of node embeddings against noise by aligning global representations of the original graph and its augmented counterpart. Local contrastive learning enforces representation consistency between functionally similar or connected nodes across diverse data sources, effectively leveraging data heterogeneity and mitigating the issue of data scarcity. The refined node representations are applied to downstream tasks, such as MDA, MTI, and DGA prediction. Experiments show GlaHGCL outperforming state-of-the-art methods, and case studies further demonstrate its ability to accurately uncover new associations among miRNAs, genes, and diseases. We have made the datasets and source code publicly available at https://github.com/Sue-syx/GlaHGCL.

HTINet2: herb-target prediction via knowledge graph embedding and residual-like graph neural network.

Target identification is one of the crucial tasks in drug research and development, as it aids in uncovering the action mechanism of herbs/drugs and discovering new therapeutic targets. Although multiple algorithms of herb target prediction have been proposed, due to the incompleteness of clinical knowledge and the limitation of unsupervised models, accurate identification for herb targets still faces huge challenges of data and models. To address this, we proposed a deep learning-based target prediction framework termed HTINet2, which designed three key modules, namely, traditional Chinese medicine (TCM) and clinical knowledge graph embedding, residual graph representation learning, and supervised target prediction. In the first module, we constructed a large-scale knowledge graph that covers the TCM properties and clinical treatment knowledge of herbs, and designed a component of deep knowledge embedding to learn the deep knowledge embedding of herbs and targets. In the remaining two modules, we designed a residual-like graph convolution network to capture the deep interactions among herbs and targets, and a Bayesian personalized ranking loss to conduct supervised training and target prediction. Finally, we designed comprehensive experiments, of which comparison with baselines indicated the excellent performance of HTINet2 (HR@10 increased by 122.7% and NDCG@10 by 35.7%), ablation experiments illustrated the positive effect of our designed modules of HTINet2, and case study demonstrated the reliability of the predicted targets of Artemisia annua and Coptis chinensis based on the knowledge base, literature, and molecular docking.

DPSG: Dynamic Propagation Social Graphs for multi-modal fake news detection

Fake news can mislead public perception and have a negative impact on people’s lives. With the increase of multi-modal news content in social media, multi-modal fake news detection has received extensive attention from researchers. However, existing methods face difficulties in capturing temporal intensity and deep social graph representations. Considering the multi-modality of news content and the relationship between entities, this paper proposes a multi-modal fake news detection model based on dynamic propagation social graph (DPSG). Specifically, it first utilizes the temporal penetration fusion block to perform multi-modal dynamic fusion on various types of nodes in the propagation sequence, and then employs dynamic signed weighting to enhance the social graph features of the propagation graph. Finally, the Transformer captures news propagation patterns and fuses multi-domain information. Experimental results on three datasets demonstrate the effectiveness of the proposed model on the fake news detection task.

Attributed graph clustering under the contrastive mechanism with cluster-preserving augmentation

Attributed graph clustering is a fundamental task in complex network analysis. Many existing graph clustering methods utilize graph representation learning techniques to learn node representations, subsequently applying K-means for clustering. Despite the significant attention and promising outcomes of graph contrastive learning in graph representation learning, we find two essential problems that need to be solved. (1) How to achieve augmentation for contrast that preserves the cluster structure of a given graph? (2) How to design an effective contrastive learning mechanism that collaborates with clustering? Therefore, we propose an attributed graph clustering method under the contrastive mechanism with cluster-preserving augmentation, integrating node representation learning and clustering into a unified framework. Specifically, we construct a contrasting view based on a generated kNN graph and edge betweenness centrality to preserve the cluster structure in the original graph. Meanwhile, a multilevel contrast mechanism based on pseudo-label-guided negative sampling is proposed to maximize the agreement between node representations in multiple latent spaces. We jointly optimize a specific clustering objective during the contrastive process, leading to refined cluster distribution directly in training. Extensive experiments on several datasets demonstrate that our proposed model consistently outperforms existing state-of-the-art methods on clustering.

RelChronVis: an interactive web application for visualizing the relative chronology of language changes

AbstractModels of the relative chronology of language changes resemble the structure of a graph. They consist of a set of changes that are in many cases related to each other. It follows that they can be visualized in a diagram, which opens up new possibilities for publishing historical linguistics data. In this paper, we introduce the RelChronVis application, a web application designed for visualizing language history. Based on detailed models of the relative chronology of Russian and Croatian sound changes, we show how interactive graph representations can help visualize language changes and the relationships between them. In addition to graphs, the application provides textual information about the included changes and relations as well as reconstructions of example lexemes. The RelChronVis application is primarily designed for doing research and for teaching. It allows the researcher to transparently compare different models and to access relevant data. At the same time, the RelChronVis application can be used to teach the history of the included languages as well as methods of historical linguistics. It provides the option of visualizing custom data and can easily be accommodated to novel discoveries. We believe that these features and uses make the RelChronVis application an immensely useful tool for publishing models of the relative chronology of language changes.

Exploring the Use of Graph Neural Networks for Blockchain Transaction Analysis and Fraud Detection

The digital system is increasing day by day while various organizations are facing problems during transactions and false activities. This research is investigating fraud detection in blockchain transactions- data used to focus on Ethereum_network. To implement the layers of Graph-Convolutional Networks (GCNs) that remain in the study, they convert blockchain transactional data into a graph structure with nodes representing addresses and edges representing transactions. The methodology includes data collection with preprocessing and graph representation in the implementation of GCN layers to analyze and detect deceitful activities. The outcomes illustration of the GNN model achieves a high accuracy score and precision with recall and F1-score. The analyses effectively identify fraudulent transactions while minimizing false positives. This work demonstrates the probability of GNNs to enhance fraud detection in blockchain systems and recommends future research directions convoluted in real-time data integration and advanced neural-network architectures toward advancing the toughness and effectiveness of fraud-detection mechanisms in trendy decentralized financial ecosystems.

Several distance and degree-based molecular structural attributes of cove-edged graphene nanoribbons

A carbon-based material with a broad scope of favourable developments is called graphene. Recently, a graphene nanoribbon with cove-edged was integrated by utilizing a bottom-up liquid-phase procedure, and it can be geometrically viewed as a hybrid of the armchair and the zigzag edges. It is indeed a type of nanoribbon containing asymmetric edges made up of sequential hexagons with impressive mechanical and electrical characteristics. Topological indices are numerical values associated with the structure of a chemical graph and are used to predict various physical, chemical, and biological properties of molecules. They are derived from the graph representation of molecules, where atoms are represented as vertices and bonds as edges. In this article, we derived the exact topological expressions of cove-edged graphene nanoribbons based on the graph-theoretical structural measures that help reduce the number of repetitive laboratory tasks necessary for studying the physicochemical characteristics of graphene nanoribbons with curved edges.