A graph G is H-free,if it contains no H as a subgraph.A graph G is said to be H-minor free,if it does not contain H as a minor.In 2010,Nikiforov asked that what the maximum spectral radius of an H-free graph of order ...A graph G is H-free,if it contains no H as a subgraph.A graph G is said to be H-minor free,if it does not contain H as a minor.In 2010,Nikiforov asked that what the maximum spectral radius of an H-free graph of order n is.In this paper,we consider some Brualdi-Solheid-Turan type problems on bipartite graphs.In 2015,Zhai,Lin and Gong in[Linear Algebra Appl.,2015,471:21-27]proved that if G is a bipartite graph with order n≥2k+2 and ρ(G)≥ρ(K_(k,n-k)),then G contains a C_(2k+2) unless G≌K_(k,n-k).First,we give a new and more simple proof for the above theorem.Second,we prove that if G is a bipartite graph with order n≥2k+2 and ρ(G)≥ρ(K_(k,n-k)),then G contains all T_(2k+3) unless G≌K_(k,n-k).Finally,we prove that among all outerplanar bipartite graphs on n≥308026 vertices,K_(1,n-1) attains the maximum spectral radius.展开更多
The definition of the ascending subgraph decomposition was given by Alavi. It has been conjectured that every graph of positive size has an ascending subgraph decomposition. In this paper it is proved that the regular...The definition of the ascending subgraph decomposition was given by Alavi. It has been conjectured that every graph of positive size has an ascending subgraph decomposition. In this paper it is proved that the regular graphs under some conditions do have an ascending subgraph decomposition.展开更多
Bollobas and Gyarfas conjectured that for n 〉 4（k - 1） every 2-edge-coloring of Kn contains a monochromatic k-connected subgraph with at least n - 2k ＋ 2 vertices. Liu, et al. proved that the conjecture holds when...Bollobas and Gyarfas conjectured that for n 〉 4（k - 1） every 2-edge-coloring of Kn contains a monochromatic k-connected subgraph with at least n - 2k ＋ 2 vertices. Liu, et al. proved that the conjecture holds when n 〉 13k - 15. In this note, we characterize all the 2-edge-colorings of Kn where each monochromatic k-connected subgraph has at most n - 2k ＋ 2 vertices for n ≥ 13k - 15.展开更多
Alavi and his fellows defined the concept of ascending subgraph decomposition of a graph and conjectured that every graph with positive size has an ascending subgraph decomposition in paper [1]. Paper [2] proved that ...Alavi and his fellows defined the concept of ascending subgraph decomposition of a graph and conjectured that every graph with positive size has an ascending subgraph decomposition in paper [1]. Paper [2] proved that K n-R n-1 has a star ascending subgraph decomposition,here K n is the complete graph with order n and R n-1 is a subgraph of K n with size at most n-1. In paper [3],Ma Kejie and Chen Huaitang proved that K n-R n has an ascending subgraph decomposition when the size of R n is not greater than n. In this paper we will prove K n-R has an ascending subgraph decomposition when the size of R is less than 3n/2. This paper will also give the concept of comet and prove that K n-R n-1 has a comet ascending subgraph decomposition.展开更多
With the development of information technology, the amount of power grid topology data has gradually increased. Therefore, accurate querying of this data has become particularly important. Several researchers have cho...With the development of information technology, the amount of power grid topology data has gradually increased. Therefore, accurate querying of this data has become particularly important. Several researchers have chosen different indexing methods in the filtering stage to obtain more optimized query results because currently there is no uniform and efficient indexing mechanism that achieves good query results. In the traditional algorithm, the hash table for index storage is prone to "collision" problems, which decrease the index construction efficiency. Aiming at the problem of quick index entry, based on the construction of frequent subgraph indexes, a method of serialized storage optimization based on multiple hash tables is proposed. This method mainly uses the exploration sequence to make the keywords evenly distributed; it avoids conflicts of the stored procedure and performs a quick search of the index. The proposed algorithm mainly adopts the "filterverify" mechanism; in the filtering stage, the index is first established offline, and then the frequent subgraphs are found using the "contains logic" rule to obtain the candidate set. Experimental results show that this method can reduce the time and scale of candidate set generation and improve query efficiency.展开更多
High-throughput techniques,such as the yeast-two-hybrid system,produce mass protein-protein interaction data. The new technique makes it possible to predict protein complexes by com-putation. A novel method,named DSDA...High-throughput techniques,such as the yeast-two-hybrid system,produce mass protein-protein interaction data. The new technique makes it possible to predict protein complexes by com-putation. A novel method,named DSDA,has been put forward to predict protein complexes via dense subgraph because the proteins among a protein complex have a much tighter relation among them than with others. This method chooses a node with its neighbors to form the initial subgraph,and chooses a node which has the tightest relation with the subgraph according to greedy strategy,then the chosen node is added into the initial subgraph until the subgraph density is below the threshold value. The ob-tained subgraph is then removed from the network and the process continues until no subgraph can be detected. Compared with other algorithms,DSDA can predict not only non-overlap protein com-plexes but also overlap protein complexes. The experiment results show that DSDA predict as many protein complexes as possible. And in Y78K network the accuracy of DSDA is as twice times as that of RNSC and MCL.展开更多
Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information ...Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information when learning discrete snapshots,resulting in insufficient network topology learning.At the same time,due to the lack of appropriate data augmentation methods,it is difficult to capture the evolving patterns of the network effectively.To address the above problems,a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs.Firstly,the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph,and the random walk is used to obtain the position representation by learning the positional information of the nodes.Secondly,a new data augmentation method is carried out from the perspectives of short-term changes and long-term stable structures of dynamic graphs.Specifically,subgraph sampling based on snapshots and global snapshots is used to obtain two structural augmentation views,and node structures and evolving patterns are learned by combining graph neural network,gated recurrent unit,and attention mechanism.Finally,the quality of node representation is improved by combining the contrastive learning between different structural augmentation views and between the two representations of structure and position.Experimental results on four real datasets show that the performance of the proposed method is better than the existing unsupervised methods,and it is more competitive than the supervised learning method under a semi-supervised setting.展开更多
A novel framework for parallel subgraph isomorphism on GPUs is proposed, named GPUSI, which consists of GPU region exploration and GPU subgraph matching. The GPUSI iteratively enumerates subgraph instances and solves ...A novel framework for parallel subgraph isomorphism on GPUs is proposed, named GPUSI, which consists of GPU region exploration and GPU subgraph matching. The GPUSI iteratively enumerates subgraph instances and solves the subgraph isomorphism in a divide-and-conquer fashion. The framework completely relies on the graph traversal, and avoids the explicit join operation. Moreover, in order to improve its performance, a task-queue based method and the virtual-CSR graph structure are used to balance the workload among warps, and warp-centric programming model is used to balance the workload among threads in a warp. The prototype of GPUSI is implemented, and comprehensive experiments of various graph isomorphism operations are carried on diverse large graphs. The experiments clearly demonstrate that GPUSI has good scalability and can achieve speed-up of 1.4–2.6 compared to the state-of-the-art solutions.展开更多
Graphs have been widely used in fields ranging from chemical informatics to social network analysis.Graph-related problems become increasingly significant,with subgraph matching standing out as one of the most challen...Graphs have been widely used in fields ranging from chemical informatics to social network analysis.Graph-related problems become increasingly significant,with subgraph matching standing out as one of the most challenging tasks.The goal of subgraph matching is to find all subgraphs in the data graph that are isomorphic to the query graph.Traditional methods mostly rely on search strategies with high computational complexity and are hard to apply to large-scale real datasets.With the advent of graph neural networks(GNNs),researchers have turned to GNNs to address subgraph matching problems.However,the multi-attributed features on nodes and edges are overlooked during the learning of graphs,which causes inaccurate results in real-world scenarios.To tackle this problem,we propose a novel model called subgraph matching on multi-attributed graph network(SGMAN).SGMAN first utilizes improved line graphs to capture node and edge features.Then,SGMAN integrates GNN and contrastive learning(CL)to derive graph representation embeddings and calculate the matching matrix to represent the matching results.We conduct experiments on public datasets,and the results affirm the superior performance of our model.展开更多
Let G be a graph, k(1), ... , k(m) be positive integers. If the edges of graph G can be decomposed into some edge disjoint [0, k(1)]-factor F-1, ..., [0, k(m)]-factor F-m, then we can say (F) over bar = {F-1, ..., F-m...Let G be a graph, k(1), ... , k(m) be positive integers. If the edges of graph G can be decomposed into some edge disjoint [0, k(1)]-factor F-1, ..., [0, k(m)]-factor F-m, then we can say (F) over bar = {F-1, ..., F-m}, is a [0, k(i)](1)(m) -factorization of G. If H is a subgraph with m edges in graph G and / E (H) boolean AND E(F-i) / = 1 for all 1 less than or equal to i less than or equal to m, then we can call that (F) over bar is orthogonal to H. It is proved that if G is a [0, k(1) + ... + k(m) - m + 1]-graph, H is a subgraph with m edges in G, then graph G has a [0, k(i)](1)(m)-factorization orthogonal to H.展开更多
In this paper, we deduce Wiener number of some connected subgraphs in tilings (4, 4, 4, 4) and (4, 6, 12), which are in Archimedean tilings. And compute their average distance.
Over the past era,subgraph mining from a large collection of graph database is a crucial problem.In addition,scalability is another big problem due to insufficient storage.There are several security challenges associa...Over the past era,subgraph mining from a large collection of graph database is a crucial problem.In addition,scalability is another big problem due to insufficient storage.There are several security challenges associated with subgraph mining in today’s on-demand system.To address this downside,our proposed work introduces a Blockchain-based Consensus algorithm for Authenticated query search in the Large-Scale Dynamic Graphs(BCCA-LSDG).The two-fold process is handled in the proposed BCCA-LSDG:graph indexing and authenticated query search(query processing).A blockchain-based reputation system is meant to maintain the trust blockchain and cloud server of the proposed architecture.To resolve the issues and provide safe big data transmission,the proposed technique also combines blockchain with a consensus algorithm architecture.Security of the big data is ensured by dividing the BC network into distinct networks,each with a restricted number of allowed entities,data kept in the cloud gate server,and data analysis in the blockchain.The consensus algorithm is crucial for maintaining the speed,performance and security of the blockchain.Then Dual Similarity based MapReduce helps in mapping and reducing the relevant subgraphs with the use of optimal feature sets.Finally,the graph index refinement process is undertaken to improve the query results.Concerning query error,fuzzy logic is used to refine the index of the graph dynamically.The proposed technique outperforms advanced methodologies in both blockchain and non-blockchain systems,and the combination of blockchain and subgraph provides a secure communication platform,according to the findings.展开更多
With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or p...With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.展开更多
Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and ...Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.展开更多
Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.Howev...Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.展开更多
Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating In...Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.展开更多
Network attacks have become a critical issue in the internet security domain.Artificial intelligence technology-based detection methodologies have attracted attention;however,recent studies have struggled to adapt to ...Network attacks have become a critical issue in the internet security domain.Artificial intelligence technology-based detection methodologies have attracted attention;however,recent studies have struggled to adapt to changing attack patterns and complex network environments.In addition,it is difficult to explain the detection results logically using artificial intelligence.We propose a method for classifying network attacks using graph models to explain the detection results.First,we reconstruct the network packet data into a graphical structure.We then use a graph model to predict network attacks using edge classification.To explain the prediction results,we observed numerical changes by randomly masking and calculating the importance of neighbors,allowing us to extract significant subgraphs.Our experiments on six public datasets demonstrate superior performance with an average F1-score of 0.960 and accuracy of 0.964,outperforming traditional machine learning and other graph models.The visual representation of the extracted subgraphs highlights the neighboring nodes that have the greatest impact on the results,thus explaining detection.In conclusion,this study demonstrates that graph-based models are suitable for network attack detection in complex environments,and the importance of graph neighbors can be calculated to efficiently analyze the results.This approach can contribute to real-world network security analyses and provide a new direction in the field.展开更多
Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where ...Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where comorbidities exacerbate outcomes.Leveraging insights from the human interactome and advancements in graph-based methodologies,this study introduces transformer with subgraph positional encoding(TSPE)for disease comorbidity prediction.Inspired by biologically supervised embedding,TSPE employs transformer's attention mechanisms and subgraph positional encoding(SPE)to capture interactions between nodes and disease associations.Our proposed SPE proves more effective than Laplacian positional encoding,as used in Dwivedi et al.'s graph transformer,underscoring the importance of integrating clustering and disease-specific information for improved predictive accuracy.Evaluated on real clinical benchmark datasets(RR0 and RR1),TSPE demonstrates substantial performance enhancements over the state-of-the-art method,achieving up to 28.24%higher ROC AUC(receiver operating characteristic-area under the curve)and 4.93%higher accuracy.This method shows promise for adaptation to other complex graph-based tasks and applications.The source code is available at GitHub website(xihan-qin/TSPE-GraphTransformer).展开更多
.The intersection power graph of a finite group G is a simple graph whose vertex set is G,in which two distinct vertices and y are adjacent if and only if either one of a and y is the identity element,or(a)n(y)is non-....The intersection power graph of a finite group G is a simple graph whose vertex set is G,in which two distinct vertices and y are adjacent if and only if either one of a and y is the identity element,or(a)n(y)is non-trivial.A number of important graph classes,including cographs,chordal graphs,split graphs,and threshold graphs,can be defined either structurally or in terms of forbidden induced subgraphs.In this paper,we characterize the finite groups whose intersection power graphs are cographs,split graphs,and threshold graphs.We also classify the finite nilpotent groups whose intersection power graphs are chordal.展开更多
基金Supported by NSFC(No.12271162)Natural Science Foundation of Shanghai(No.22ZR1416300).
文摘A graph G is H-free,if it contains no H as a subgraph.A graph G is said to be H-minor free,if it does not contain H as a minor.In 2010,Nikiforov asked that what the maximum spectral radius of an H-free graph of order n is.In this paper,we consider some Brualdi-Solheid-Turan type problems on bipartite graphs.In 2015,Zhai,Lin and Gong in[Linear Algebra Appl.,2015,471:21-27]proved that if G is a bipartite graph with order n≥2k+2 and ρ(G)≥ρ(K_(k,n-k)),then G contains a C_(2k+2) unless G≌K_(k,n-k).First,we give a new and more simple proof for the above theorem.Second,we prove that if G is a bipartite graph with order n≥2k+2 and ρ(G)≥ρ(K_(k,n-k)),then G contains all T_(2k+3) unless G≌K_(k,n-k).Finally,we prove that among all outerplanar bipartite graphs on n≥308026 vertices,K_(1,n-1) attains the maximum spectral radius.
文摘The definition of the ascending subgraph decomposition was given by Alavi. It has been conjectured that every graph of positive size has an ascending subgraph decomposition. In this paper it is proved that the regular graphs under some conditions do have an ascending subgraph decomposition.
基金Supported by the National Natural Science Foundation of China(10701065 and 11101378)Zhejiang Provincial Natural Science Foundation(LY14A010009)
文摘Bollobas and Gyarfas conjectured that for n 〉 4（k - 1） every 2-edge-coloring of Kn contains a monochromatic k-connected subgraph with at least n - 2k ＋ 2 vertices. Liu, et al. proved that the conjecture holds when n 〉 13k - 15. In this note, we characterize all the 2-edge-colorings of Kn where each monochromatic k-connected subgraph has at most n - 2k ＋ 2 vertices for n ≥ 13k - 15.
文摘Alavi and his fellows defined the concept of ascending subgraph decomposition of a graph and conjectured that every graph with positive size has an ascending subgraph decomposition in paper [1]. Paper [2] proved that K n-R n-1 has a star ascending subgraph decomposition,here K n is the complete graph with order n and R n-1 is a subgraph of K n with size at most n-1. In paper [3],Ma Kejie and Chen Huaitang proved that K n-R n has an ascending subgraph decomposition when the size of R n is not greater than n. In this paper we will prove K n-R has an ascending subgraph decomposition when the size of R is less than 3n/2. This paper will also give the concept of comet and prove that K n-R n-1 has a comet ascending subgraph decomposition.
基金supported by the State Grid Science and Technology Project (Title: Research on High Performance Analysis Technology of Power Grid GIS Topology Based on Graph Database, 5455HJ160005)
文摘With the development of information technology, the amount of power grid topology data has gradually increased. Therefore, accurate querying of this data has become particularly important. Several researchers have chosen different indexing methods in the filtering stage to obtain more optimized query results because currently there is no uniform and efficient indexing mechanism that achieves good query results. In the traditional algorithm, the hash table for index storage is prone to "collision" problems, which decrease the index construction efficiency. Aiming at the problem of quick index entry, based on the construction of frequent subgraph indexes, a method of serialized storage optimization based on multiple hash tables is proposed. This method mainly uses the exploration sequence to make the keywords evenly distributed; it avoids conflicts of the stored procedure and performs a quick search of the index. The proposed algorithm mainly adopts the "filterverify" mechanism; in the filtering stage, the index is first established offline, and then the frequent subgraphs are found using the "contains logic" rule to obtain the candidate set. Experimental results show that this method can reduce the time and scale of candidate set generation and improve query efficiency.
基金Supported by the National Natural Science Foundation of China (60803025)
文摘High-throughput techniques,such as the yeast-two-hybrid system,produce mass protein-protein interaction data. The new technique makes it possible to predict protein complexes by com-putation. A novel method,named DSDA,has been put forward to predict protein complexes via dense subgraph because the proteins among a protein complex have a much tighter relation among them than with others. This method chooses a node with its neighbors to form the initial subgraph,and chooses a node which has the tightest relation with the subgraph according to greedy strategy,then the chosen node is added into the initial subgraph until the subgraph density is below the threshold value. The ob-tained subgraph is then removed from the network and the process continues until no subgraph can be detected. Compared with other algorithms,DSDA can predict not only non-overlap protein com-plexes but also overlap protein complexes. The experiment results show that DSDA predict as many protein complexes as possible. And in Y78K network the accuracy of DSDA is as twice times as that of RNSC and MCL.
文摘Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information when learning discrete snapshots,resulting in insufficient network topology learning.At the same time,due to the lack of appropriate data augmentation methods,it is difficult to capture the evolving patterns of the network effectively.To address the above problems,a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs.Firstly,the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph,and the random walk is used to obtain the position representation by learning the positional information of the nodes.Secondly,a new data augmentation method is carried out from the perspectives of short-term changes and long-term stable structures of dynamic graphs.Specifically,subgraph sampling based on snapshots and global snapshots is used to obtain two structural augmentation views,and node structures and evolving patterns are learned by combining graph neural network,gated recurrent unit,and attention mechanism.Finally,the quality of node representation is improved by combining the contrastive learning between different structural augmentation views and between the two representations of structure and position.Experimental results on four real datasets show that the performance of the proposed method is better than the existing unsupervised methods,and it is more competitive than the supervised learning method under a semi-supervised setting.
基金Projects(61272142,61103082,61003075,61170261,61103193)supported by the National Natural Science Foundation of ChinaProject supported by Funds for New Century Excellent Talents in University of ChinaProjects(2012AA01A301,2012AA010901)supported by the National High Technology Research and Development Program of China
文摘A novel framework for parallel subgraph isomorphism on GPUs is proposed, named GPUSI, which consists of GPU region exploration and GPU subgraph matching. The GPUSI iteratively enumerates subgraph instances and solves the subgraph isomorphism in a divide-and-conquer fashion. The framework completely relies on the graph traversal, and avoids the explicit join operation. Moreover, in order to improve its performance, a task-queue based method and the virtual-CSR graph structure are used to balance the workload among warps, and warp-centric programming model is used to balance the workload among threads in a warp. The prototype of GPUSI is implemented, and comprehensive experiments of various graph isomorphism operations are carried on diverse large graphs. The experiments clearly demonstrate that GPUSI has good scalability and can achieve speed-up of 1.4–2.6 compared to the state-of-the-art solutions.
文摘Graphs have been widely used in fields ranging from chemical informatics to social network analysis.Graph-related problems become increasingly significant,with subgraph matching standing out as one of the most challenging tasks.The goal of subgraph matching is to find all subgraphs in the data graph that are isomorphic to the query graph.Traditional methods mostly rely on search strategies with high computational complexity and are hard to apply to large-scale real datasets.With the advent of graph neural networks(GNNs),researchers have turned to GNNs to address subgraph matching problems.However,the multi-attributed features on nodes and edges are overlooked during the learning of graphs,which causes inaccurate results in real-world scenarios.To tackle this problem,we propose a novel model called subgraph matching on multi-attributed graph network(SGMAN).SGMAN first utilizes improved line graphs to capture node and edge features.Then,SGMAN integrates GNN and contrastive learning(CL)to derive graph representation embeddings and calculate the matching matrix to represent the matching results.We conduct experiments on public datasets,and the results affirm the superior performance of our model.
文摘Let G be a graph, k(1), ... , k(m) be positive integers. If the edges of graph G can be decomposed into some edge disjoint [0, k(1)]-factor F-1, ..., [0, k(m)]-factor F-m, then we can say (F) over bar = {F-1, ..., F-m}, is a [0, k(i)](1)(m) -factorization of G. If H is a subgraph with m edges in graph G and / E (H) boolean AND E(F-i) / = 1 for all 1 less than or equal to i less than or equal to m, then we can call that (F) over bar is orthogonal to H. It is proved that if G is a [0, k(1) + ... + k(m) - m + 1]-graph, H is a subgraph with m edges in G, then graph G has a [0, k(i)](1)(m)-factorization orthogonal to H.
文摘In this paper, we deduce Wiener number of some connected subgraphs in tilings (4, 4, 4, 4) and (4, 6, 12), which are in Archimedean tilings. And compute their average distance.
文摘Over the past era,subgraph mining from a large collection of graph database is a crucial problem.In addition,scalability is another big problem due to insufficient storage.There are several security challenges associated with subgraph mining in today’s on-demand system.To address this downside,our proposed work introduces a Blockchain-based Consensus algorithm for Authenticated query search in the Large-Scale Dynamic Graphs(BCCA-LSDG).The two-fold process is handled in the proposed BCCA-LSDG:graph indexing and authenticated query search(query processing).A blockchain-based reputation system is meant to maintain the trust blockchain and cloud server of the proposed architecture.To resolve the issues and provide safe big data transmission,the proposed technique also combines blockchain with a consensus algorithm architecture.Security of the big data is ensured by dividing the BC network into distinct networks,each with a restricted number of allowed entities,data kept in the cloud gate server,and data analysis in the blockchain.The consensus algorithm is crucial for maintaining the speed,performance and security of the blockchain.Then Dual Similarity based MapReduce helps in mapping and reducing the relevant subgraphs with the use of optimal feature sets.Finally,the graph index refinement process is undertaken to improve the query results.Concerning query error,fuzzy logic is used to refine the index of the graph dynamically.The proposed technique outperforms advanced methodologies in both blockchain and non-blockchain systems,and the combination of blockchain and subgraph provides a secure communication platform,according to the findings.
基金funded by the Hunan Provincial Natural Science Foundation of China(Grant No.2025JJ70105)the Hunan Provincial College Students’Innovation and Entrepreneurship Training Program(Project No.S202411342056)The article processing charge(APC)was funded by the Project No.2025JJ70105.
文摘With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01296).
文摘Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.
基金funded by the National Key Research and Development Program of China(Grant No.2024YFE0209000)the NSFC(Grant No.U23B2019).
文摘Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.
文摘Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the ICAN(ICT Challenge and Advanced Network of HRD)support program(IITP-2025-RS-2023-00259497)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)and was supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Republic of Korea government(MSIT)(No.IITP-2025-RS-2023-00254129+1 种基金Graduate School of Metaverse Convergence(Sungkyunkwan University))was supported by the Basic Science Research Program of the National Research Foundation(NRF)funded by the Republic of Korean government(MSIT)(No.RS-2024-00346737).
文摘Network attacks have become a critical issue in the internet security domain.Artificial intelligence technology-based detection methodologies have attracted attention;however,recent studies have struggled to adapt to changing attack patterns and complex network environments.In addition,it is difficult to explain the detection results logically using artificial intelligence.We propose a method for classifying network attacks using graph models to explain the detection results.First,we reconstruct the network packet data into a graphical structure.We then use a graph model to predict network attacks using edge classification.To explain the prediction results,we observed numerical changes by randomly masking and calculating the importance of neighbors,allowing us to extract significant subgraphs.Our experiments on six public datasets demonstrate superior performance with an average F1-score of 0.960 and accuracy of 0.964,outperforming traditional machine learning and other graph models.The visual representation of the extracted subgraphs highlights the neighboring nodes that have the greatest impact on the results,thus explaining detection.In conclusion,this study demonstrates that graph-based models are suitable for network attack detection in complex environments,and the importance of graph neighbors can be calculated to efficiently analyze the results.This approach can contribute to real-world network security analyses and provide a new direction in the field.
文摘Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where comorbidities exacerbate outcomes.Leveraging insights from the human interactome and advancements in graph-based methodologies,this study introduces transformer with subgraph positional encoding(TSPE)for disease comorbidity prediction.Inspired by biologically supervised embedding,TSPE employs transformer's attention mechanisms and subgraph positional encoding(SPE)to capture interactions between nodes and disease associations.Our proposed SPE proves more effective than Laplacian positional encoding,as used in Dwivedi et al.'s graph transformer,underscoring the importance of integrating clustering and disease-specific information for improved predictive accuracy.Evaluated on real clinical benchmark datasets(RR0 and RR1),TSPE demonstrates substantial performance enhancements over the state-of-the-art method,achieving up to 28.24%higher ROC AUC(receiver operating characteristic-area under the curve)and 4.93%higher accuracy.This method shows promise for adaptation to other complex graph-based tasks and applications.The source code is available at GitHub website(xihan-qin/TSPE-GraphTransformer).
基金supported by the National Natural Science Foundation of China(Grant Nos.11801441,61976244)the Natural Science Basic Research Program of Shaanxi(Program No.2020JQ-761)the Shaanxi Fundamental Science Research Project for Mathematics and Physics(Grant No.22JSQ024).
文摘.The intersection power graph of a finite group G is a simple graph whose vertex set is G,in which two distinct vertices and y are adjacent if and only if either one of a and y is the identity element,or(a)n(y)is non-trivial.A number of important graph classes,including cographs,chordal graphs,split graphs,and threshold graphs,can be defined either structurally or in terms of forbidden induced subgraphs.In this paper,we characterize the finite groups whose intersection power graphs are cographs,split graphs,and threshold graphs.We also classify the finite nilpotent groups whose intersection power graphs are chordal.
