Graph Data Analysis Research Articles

Portable Network Resolving Huge-Graph Isomorphism Problem

Abstract The graph isomorphism, as a key task in graph data analysis, is of great significance for the understanding, feature extraction, and pattern recognition of graph data. The best performance of traditional methods is the quasi-polynomial time complexity, which is infeasible for huge graphs. This paper aims to propose a lightweight graph network to resolve the problem of isomorphism in huge graphs. We propose a partitioning algorithm with linear time complexity based on isomorphic necessary condition to handle network graphs that cannot be fully computed by a single computer. We use anti-weight convolution analysis and skip connections to obtain a more stable representation with fewer layers and parameters. We implement simulations on personal computer (PC) with graphs consisting of hundred millions of edges, demonstrating the identification performance ($>98\%$) and time efficiency.

Distributed Data Analysis in Cloud Services for Insurance Companies

This article embarks on an insightful journey through the realm of advanced data analysis techniques which can be used in the insurance area, with a keen focus on the applications and capabilities of Graph Neural Networks (GNN) in the following sector. The article is structured into several chapters, which include the overview of existing and commonly used approaches of the data representation, the possible ways of data analysis of the data in such a representation, deep dive into the concept of GNN for the graph data analysis and the applicability of each approach in the insurance industry. The initial chapter introduces the two main concepts of the data representation, which are the commonly used relational database and the more modern approach of dimensional data design. Then the focus is moved to the graph data representation, which also can be used for data analysis in the cloud environment. To achieve the best applicability in the insurance industry, particularly in underwriting and claims management, the article analyzes the advantages of each approach to the data representation as well as its drawbacks. To conclude the chapter, the comparison table of the three approaches is presented. Based on the comparison table, the decision to use the graph representation is made as it enables the industry to unravel complex relationships and dependencies amid various data points—such as policyholder history, incident particulars, and third-party information—resulting in more accurate risk assessments and efficient claim resolutions. Then the article presents the concept of Graph Neural Networks, a rather new concept which can be used to analyze the data, represented in a graph form using machine learning algorithms. The potential of using this approach for the data analysis in the insurance area and some possible use cases are described. The advantages of using this approach include ability to effectively capture and leverage the complex relationships inherent in graph- structured data and a powerful framework for analyzing and processing graph-structured data. However, the potential drawbacks of the approach such as complexity to design and difficulties in scaling are also considered. Further along, the article probes the strategic integration of Graph Neural Networks with real-time and dynamic data environments, examining their adaptability to evolving network patterns and temporal dependencies. We discuss how this adaptability is paramount in contexts like real-time decision-making and predictive analysis, which are crucial for staying agile in a rapidly changing market landscape. Then the exact use cases of the GNN applicability in the insurance area are provided, including the claim assignment and underwriting process are described in detail. Furthermore, the simplified mathematical formulation of the underwriting process is provided, which elaborates the role GNNs play in propelling actuarial science with their capability to incorporate node attributes, edge information, and graph structure into a composite risk assessment algorithm. The article concludes by describing that with the new technologies, the graph representation may become the new standard for the data analysis in the cloud environment, especially for the insurance area, stressing the pivotal role of GNNs in navigating the complexities of interconnected, dynamic data and advocating for their continued research and development to unlock even greater potentials across various sectors.

Enhancing graph convolutional networks with progressive granular ball sampling fusion: A novel approach to efficient and accurate GCN training

Graph convolutional network (GCN) has gained considerable attention and has been widely utilized in graph data analytics. However, training large GCNs presents considerable challenges owing to the inherent complexity of graph-structured data. Previous training algorithms frequently struggle with slow convergence speed caused by full-batch gradient descent on entire graphs and reduced model performance due to inappropriate node sampling methods. To address these issues, we propose a novel framework called Progressive Granular Ball Sampling Fusion (PGBSF). PGBSF leverages granular ball sampling to partition the original graph into a collection of subgraphs, thereby enhancing both training efficiency and detail capture. Then, it applies a progressive approach accompanied by a parameter-sharing strategy for incremental GCN model training, which results in robust performance and rapid convergence speed. This simple yet effective strategy considerably enhances classification accuracy and memory efficiency. The experiment results show that our proposed architecture consistently outperforms other baseline models in terms of accuracy across almost all datasets with different label rates. In addition, PGBSF improves GCN performance significantly on large and complex datasets. Moreover, GCN+PGBSF reduces time complexity by training on subgraphs and achieves the fastest convergence speed among all models, with a relatively small variance in loss during training.

I/O Efficient Label-Constrained Reachability Queries in Large Graphs

Computing the reachability between two vertices in a graph is a fundamental problem in graph data analysis. Most of the existing works assume that the edges in the graph have no labels, but in many real application scenarios, edges naturally come with edge-labels, and label constraints may be placed on the edges appearing on a valid path between two query vertices. Therefore, we study the label-constrained reachability (LCR) queries in this paper, where we are given a source vertex s , a target vertex t , a label set Δ, and the goal is to check whether there exists any path from s to t such that all the labels of edges on the path belong to Δ. A plethora of methods have been proposed in the literature to support the LCR queries. All these methods take the assumption that the graph is resident in the main memory of a machine. Nevertheless, the graphs in many real application scenarios are generally big and may not reside in memory. In these cases, existing methods suffer from serious scalability problem, i.e., result in huge I/O costs. Motivated by this, in this paper, we study the I/O efficient LCR query problem and aim to efficiently answer the LCR queries when the graph cannot fit in the main memory. To achieve this goal, we propose a reduction-based indexing approach. We introduce two elegant graph reduction operators which aims to reduce the size of the graph loaded in memory while preserving the LCR information among the remaining vertices. With these two operators, we devise an index named LCR-Index and propose algorithms to adaptively construct the index based on the available memory. Equipped with LCR-Index, we can answer a LCR query by only scanning the LCR-Index sequentially. Experiments demonstrate our query processing algorithm can handle graphs with billions of edges.

Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification.

Graph classification plays an important role in a wide range of applications from biological prediction to social analysis. Traditional graph classification models built on graph kernels are hampered by the challenge of poor generalization as they are heavily dependent on the dedicated design of handcrafted features. Recently, graph neural networks (GNNs) become a new class of tools for analyzing graph data and have achieved promising performance. However, it is necessary to collect a large number of labeled graph data for training an accurate GNN, which is often unaffordable in real-world applications. Therefore, it is an open question to build GNNs under the condition of few-shot learning where only a few labeled graphs are available. In this article, we introduce a new Structure-aware Prototypical Neural Process (SPNP for short) for a few-shot graph classification. Specifically, at the encoding stage, SPNP first employs GNNs to capture graph structure information. Then, SPNP incorporates such structural priors into the latent path and the deterministic path for representing stochastic processes. At the decoding stage, SPNP uses a new prototypical decoder to define a metric space where unseen graphs can be predicted effectively. The proposed decoder, which contains a self-attention mechanism to learn the intraclass dependence between graphs, can enhance the class-level representations, especially for new classes. Furthermore, benefited from such a flexible encoding-decoding architecture, SPNP can directly map the context samples to a predictive distribution without any complicated operations used in previous methods. Extensive experiments demonstrate that SPNP achieves consistent and significant improvements over state-of-the-art methods. Further discussions are provided toward model efficiency and more detailed analysis.

Random Sampling Method of Large-Scale Graph Data Classification

Graph data appears in broad real-world applications in modelling complex objects in big data. Effective analysis of graph data provides a deeper understanding of the data in data mining tasks, including classification, clustering, prediction, and recommendation systems. Mining a large number of graphs becomes a challenging task because state-of-the-art methods are not scalable due to the memory limit. To address this issue, we propose a novel approximate random sampling method for large-scale graph data classification. In this approach, we applied a representation method to encode each graph as a record of a vector string and a set of graphs as a set of N records in a file. Then, we partition the set of records into disjoint subsets of data blocks, making each data block a random sample of the data file. After that, we randomly select a subset of data blocks, each being a random sample of the graph dataset, and compute the different graph property distributions. Since the data blocks in this model are much smaller than the entire data set, it is more efficient to analyze them on a standalone small machine, and multiple data blocks can be analyzed on multiple nodes of the cluster in parallel. Finally, we classified the graphs of data blocks using the SVM algorithm. In experimental evaluation, our proposed method outperformed state-of-the-art graph kernels on graph classification datasets in terms of accuracy.

Performance Evaluation of Graph Neural Network-Based RouteNet Model with Attention Mechanism

Graph representation is recognized as an efficient method for modeling networks, precisely illustrating intricate, dynamic interactions within various entities of networks by representing entities as nodes and their relationships as edges. Leveraging the advantage of the network graph data along with deep learning technologies specialized for analyzing graph data, Graph Neural Networks (GNNs) have revolutionized the field of computer networking by effectively handling structured graph data and enabling precise predictions for various use cases such as performance modeling, routing optimization, and resource allocation. The RouteNet model, utilizing a GNN, has been effectively applied in determining Quality of Service (QoS) parameters for each source-to-destination pair in computer networks. However, a prevalent issue in the current GNN model is their struggle with generalization and capturing the complex relationships and patterns within network data. This research aims to enhance the predictive power of GNN-based models by enhancing the original RouteNet model by incorporating an attention layer into its architecture. A comparative analysis is conducted to evaluate the performance of the Modified RouteNet model against the Original RouteNet model. The effectiveness of the added attention layer has been examined to determine its impact on the overall model performance. The outcomes of this research contribute to advancing GNN-based network performance prediction, addressing the limitations of existing models, and providing reliable frameworks for predicting network delay.

On inference for modularity statistics in structured networks

This paper revisits the classical concept of network modularity and its spectral relaxations used throughout graph data analysis. We formulate and study several modularity statistic variants for which we establish asymptotic distributional results in the large-network limit for networks exhibiting nodal community structure. Our work facilitates testing for network differences and can be used in conjunction with existing theoretical guarantees for stochastic blockmodel random graphs. Our results are enabled by recent advances in the study of low-rank truncations of large network adjacency matrices. We provide confirmatory simulation studies and real data analysis pertaining to the network neuroscience study of psychosis, specifically schizophrenia. Collectively, this paper contributes to the limited existing literature to date on statistical inference for modularity-based network analysis. Supplemental materials for this article are available online.

Structural Entropy Based Graph Structure Learning for Node Classification

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

Dynamic Reactive Spiking Graph Neural Network

Spiking Graph Neural Networks are emerging tools for analyzing graph data along with low energy consumption and certain biological fidelity. Existing methods directly integrate same-reactive spiking neurons into graph neural networks for processing propagated graphs. However, such same-reactive neurons are not biological-functionality enough compared to the brain's dynamic-reactive ones, limiting the model's expression. Meanwhile, insufficient long-range neighbor information can be excavated with the few-step propagated graph, restricting discrimination of graph spiking embeddings. Inspired by the dynamic cognition in the brain, we propose a Dynamic Reactive Spiking Graph Neural Network that can enhance model's expressive ability in higher biological fidelity. Specifically, we design dynamic reactive spiking neurons to process spiking graph inputs, which have unique optimizable thresholds to spontaneously explore dynamic reactive states between neurons. Moreover, discriminative graph positional spikes are learned and integrated adaptively into spiking outputs through our neurons, thereby exploring long-range neighbors more thoroughly. Finally, with the dynamic reactive mechanism and learnable positional integration, we can obtain a powerful and highly bio-fidelity model with low energy consumption. Experiments on various domain-related datasets can demonstrate the effectiveness of our model. Our code is available at https://github.com/hzhao98/DRSGNN.

AOPWIKI-EXPLORER: An interactive graph-based query engine leveraging large language models

Adverse Outcome Pathways (AOPs) provide a basis for non-animal testing, by outlining the cascade of molecular and cellular events initiated upon stressor exposure, leading to adverse effects. In recent years, the scientific community has shown interest in developing AOPs through crowdsourcing, with the results archived in the AOP-Wiki: a centralized repository coordinated by the OECD, hosting nearly 512 AOPs (April, 2023). However, the AOP-Wiki platform currently lacks a versatile querying system, which hinders developers' exploration of the AOP network and impedes its practical use in risk assessment. This work proposes to unleash the full potential of the AOP-Wiki archive by adapting its data into a Labelled Property Graph (LPG) schema. Additionally, the tool offers a visual network query interface for both database-specific and natural language queries, facilitating the retrieval and analysis of graph data. The multi-query interface allows non-technical users to construct flexible queries, thereby enhancing the potential for AOP exploration. By reducing the time and technical requirements, the present query engine enhances the practical utilization of the valuable data within AOP-Wiki. To evaluate the platform, a case study is presented with three levels of use-case scenarios (simple, moderate, and complex queries). AOPWIKI-EXPLORER is freely available on GitHub (https://github.com/Crispae/AOPWiki_Explorer) for wider community reach and further enhancement.

Locally and Structurally Private Graph Neural Networks

Graph Neural Networks (GNNs) are known to address such tasks over graph-structured data, which is widely used to represent many real-world systems. The collection and analysis of graph data using GNNs raise significant privacy concerns regarding disclosing sensitive information. Existing works in privacy-preserving GNNs ensure the privacy of nodes’ features and labels. However, its structure also needs to be privatized. To address this problem, we provide a method, Local Structural Perturbation Graph Neural Network, that adds noise to the neighborhood data of the node along with its features and label. Here, we perturb the graph structure by sampling non-neighboring nodes and randomizing them along with the neighborhood. We use differentially private mechanisms to perturb the structure of graphs with theoretical guarantees. This introduces the challenge of reducing the impact of noise in the neighborhood on accuracy. In this view, we use the p -hop neighborhood to compensate for the loss of actual neighbors in randomization. We use the node and label privacy as implemented in the previous methods for privacy in GNNs. We conduct extensive experiments over real-world datasets to show the impact of perturbation on the graph structure. We also perform the theoretical analysis of our proposed method.

Integrating Machine Learning in Anti-Money Laundering through Crypto: A Comprehensive Performance Review

The integration of machine learning (ML) algorithms in Anti-Money Laundering (AML) practices has garnered significant attention due to its potential to enhance the detection and prevention of illicit activities in the cryptocurrency ecosystem. This systematic literature review analysed the effectiveness of integrating ML algorithms in detecting and preventing crypto laundering activities, identify the most frequently used ML algorithms, examine trends in publication and research methodologies, and discuss key challenges and constraints associated with integrating ML technologies into AML frameworks. A comprehensive search strategy was employed to identify relevant studies, resulting in the inclusion of 52 articles published between 2019 and 2023. The findings reveal a growing interest in the field, with a notable increase in publications in recent years. Traditional ML models such as Logistic Regression, Random Forest, and Support Vector Machine (SVM) remain prevalent, while deep learning models like Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks are gaining popularity. Graph Convolutional Networks (GCNs) have emerged as a significant area of exploration, particularly in the context of graph data analysis in cryptocurrencies. Despite advancements in ML, cryptocurrencies continue to pose a high risk of money laundering due to the practical challenge of implementation ownership of the various ML models. Future research should focus on how these challenges will be addressed to ensure the effective and sustainable use of ML technologies in real-world AML practices.

Image and video analysis using graph neural network for Internet of Medical Things and computer vision applications

AbstractGraph neural networks (GNNs) have revolutionised the processing of information by facilitating the transmission of messages between graph nodes. Graph neural networks operate on graph‐structured data, which makes them suitable for a wide variety of computer vision problems, such as link prediction, node classification, and graph classification. The authors explore in depth the applications of GNNs in computer vision, including their design considerations, architectural challenges, applications, and implementation concerns. While conventional convolutional neural networks (CNNs) excel at object recognition in images and videos, GNN architectures offer a novel method for addressing various image and video comprehension challenges. A novel deep neural network‐based model for image and video analysis is proposed, which combines a neural network with fully connected layers on a graph. The proposed architecture extracts highly discriminative information from images and videos by leveraging the graph structure. Also, the investigation focuses on the enhancement of underlying connection network estimation using cutting‐edge graph learning algorithms. Experimental results on real‐world datasets demonstrate that the proposed GNN model is preferable to existing state‐of‐the‐art methods. It obtains a remarkable 96.63% accuracy on the ImageNet dataset, outperforming heuristic approaches, artificial neural networks, and conventional CNN techniques. From the results, we can see that GNNs are a potent instrument for graph data analysis and pave the way for machines to achieve human‐level visual intuition.

LM-SRPQ: Efficiently Answering Regular Path Query in Streaming Graphs

Regular path query (RPQ) is a basic operation for graph data analysis, and persistent RPQ in streaming graphs is a new-emerging research topic. In this paper, we propose a novel algorithm for persistent RPQ in streaming graphs, named LM-SRPQ. It solves persistent RPQ with a combination of intermediate result materialization and real-time graph traversal. Compared to prior art, it merges redundant storage and computation, achieving higher memory and time efficiency. We carry out extensive experiments with both real-world and synthetic streaming graphs to evaluate its performance. Experiment results confirm its superiority compared to prior art in both memory and time efficiency.

Bearing Fault Diagnosis Based on Graph Formulation and Graph Convolutional Network

Bearing fault diagnosis stands as a critical component in the maintenance of rotating machinery. Many prevalent deep learning techniques are tailored to Euclidean datasets such as audio, image, and video. However, these methods falter when confronting non-Euclidean datasets, notably graph representations. In response, here we introduce an innovative approach harnessing the Graph Convolutional Network (GCN) to analyze graph data derived from vibration signals related to bearing faults. This enhances the precision and reliability of fault diagnosis. Our methodology initiates by deriving a periodogram from the unprocessed vibration signals. Subsequently, this periodogram is mapped into a graph format, upon which the GCN is engaged for classification purposes. We substantiate the efficacy of our approach through rigorous experimental assessments conducted on a collection of ten bearing sets. Within these experiments, an accelerometer chronicles vibration signals across varying load conditions. We probe into the diagnostic accuracy rates across diverse loads and Signal-to-Noise Ratios (SNRs). Furthermore, a comparative evaluation of our method against several established algorithms delineated in this study is undertaken. Empirical observations confirm that our GCN-based strategy registers an elevated diagnostic accuracy quotient.

FedGL: Federated graph learning framework with global self-supervision

Graph data are ubiquitous in the real world. Graph learning (GL) attempts to mine and analyze graph data so that valuable information can be discovered. Existing GL methods are designed for centralized scenarios. However, in practical scenarios, graph data are usually distributed across different organizations, resulting in isolated data silos. To address this problem, we incorporate federated learning into GL and propose a general Federated Graph Learning framework called FedGL. FedGL is capable of obtaining a high-quality global graph model while protecting data privacy by discovering the global self-supervision information during the federated training. Specifically, we propose uploading prediction results and node embeddings to the server for discovering the global pseudo labels and global pseudo graph. These are then distributed to each client to enrich the training labels and complement the graph structure respectively, thereby improving the quality of each local model. Moreover, the global self-supervision enables information of each client to flow and be shared in a privacy-preserving manner, thus alleviating the heterogeneity and utilizing the complementarity of graph data among different clients. Finally, experimental results show that FedGL significantly outperforms baselines on four widely used graph datasets.

Graph embedding and geometric deep learning relevance to network biology and structural chemistry.

Graphs are used as a model of complex relationships among data in biological science since the advent of systems biology in the early 2000. In particular, graph data analysis and graph data mining play an important role in biology interaction networks, where recent techniques of artificial intelligence, usually employed in other type of networks (e.g., social, citations, and trademark networks) aim to implement various data mining tasks including classification, clustering, recommendation, anomaly detection, and link prediction. The commitment and efforts of artificial intelligence research in network biology are motivated by the fact that machine learning techniques are often prohibitively computational demanding, low parallelizable, and ultimately inapplicable, since biological network of realistic size is a large system, which is characterised by a high density of interactions and often with a non-linear dynamics and a non-Euclidean latent geometry. Currently, graph embedding emerges as the new learning paradigm that shifts the tasks of building complex models for classification, clustering, and link prediction to learning an informative representation of the graph data in a vector space so that many graph mining and learning tasks can be more easily performed by employing efficient non-iterative traditional models (e.g., a linear support vector machine for the classification task). The great potential of graph embedding is the main reason of the flourishing of studies in this area and, in particular, the artificial intelligence learning techniques. In this mini review, we give a comprehensive summary of the main graph embedding algorithms in light of the recent burgeoning interest in geometric deep learning.

Fast Maximal Quasi-clique Enumeration: A Pruning and Branching Co-Design Approach

Mining cohesive subgraphs from a graph is a fundamental problem in graph data analysis. One notable cohesive structure is γ-quasi-clique (QC), where each vertex connects at least a fraction γ of the other vertices inside. Enumerating maximal γ-quasi-cliques (MQCs) of a graph has been widely studied and used for many applications such as community detection and significant biomolecule structure discovery. One common practice of finding all MQCs is to (1) find a set of QCs containing all MQCs and then (2) filter out non-maximal QCs. While quite a few algorithms have been developed (which are branch-and-bound algorithms) for finding a set of QCs that contains all MQCs, all focus on sharpening the pruning techniques and devote little effort to improving the branching part. As a result, they provide no guarantee on pruning branches and all have the worst-case time complexity of O*(2n), where O* suppresses the polynomials and n is the number of vertices in the graph. In this paper, we focus on the problem of finding a set of QCs containing all MQCs but deviate from further sharpening the pruning techniques as existing methods do. We pay attention to both the pruning and branching parts and develop new pruning techniques and branching methods that would suit each other better towards pruning more branches both theoretically and practically. Specifically, we develop a new branch-and-bound algorithm called FastQC based on newly developed pruning techniques and branching methods, which improves the worst-case time complexity to O*(αkn), where αk is a positive real number strictly smaller than 2. Furthermore, we develop a divide-and-conquer strategy for boosting the performance of FastQC. Finally, we conduct extensive experiments on both real and synthetic datasets, and the results show that our algorithms are up to two orders of magnitude faster than the state-of-the-art on real datasets.

Fairness-Aware Maximal Clique in Large Graphs: Concepts and Algorithms

Cohesive subgraph mining on attributed graphs is a fundamental problem in graph data analysis. Existing cohesive subgraph mining algorithms on attributed graphs do not consider the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fairness</i> of attributes in the subgraph. In this paper, we, for the first time, introduce fairness into the widely-used clique model to mine fairness-aware cohesive subgraphs. In particular, we propose three novel fairness-aware maximal clique models on attributed graphs, called weak fair clique, strong fair clique and relative fair clique, respectively. To enumerate all weak fair cliques, we develop an efficient backtracking algorithm called WFCEnum equipped with a novel colorful <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -core based pruning technique. We also propose an efficient enumeration algorithm called SFCEnum to find all strong fair cliques based on a new attribute-alternatively-selection search technique. To further improve the efficiency, we also present several non-trivial ordering techniques for both weak and strong fair clique enumerations. To enumerate all relative fair cliques, we design an enhanced colorful <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -core based pruning technique for 2D attributes, and develop two efficient search algorithms: RFCRefineEnum and RFCAlterEnum for arbitrary dimension attributes. The results of extensive experiments on four real-world graphs demonstrate the efficiency, scalability and effectiveness of the proposed algorithms.