In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with l...In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.展开更多
In the tobacco industry,insider employee attack is a thorny problem that is difficult to detect.To solve this issue,this paper proposes an insider threat detection method based on heterogeneous graph embedding.First,t...In the tobacco industry,insider employee attack is a thorny problem that is difficult to detect.To solve this issue,this paper proposes an insider threat detection method based on heterogeneous graph embedding.First,the interrelationships between logs are fully considered,and log entries are converted into heterogeneous graphs based on these relationships.Second,the heterogeneous graph embedding is adopted and each log entry is represented as a low-dimensional feature vector.Then,normal logs and malicious logs are classified into different clusters by clustering algorithm to identify malicious logs.Finally,the effectiveness and superiority of the method is verified through experiments on the CERT dataset.The experimental results show that this method has better performance compared to some baseline methods.展开更多
In recent years,online reservation systems of country hotel have become increasingly popular in rural areas.How to accurately recommend the houses of country hotel to the users is an urgent problem to be solved.Aiming...In recent years,online reservation systems of country hotel have become increasingly popular in rural areas.How to accurately recommend the houses of country hotel to the users is an urgent problem to be solved.Aiming at the problem of cold start and data sparseness in recommendation,a Hybrid Recommendation method based on Graph Embedding(HRGE)is proposed.First,three types of network are built,including user-user network based on user tag,househouse network based on house tag,and user-user network based on user behavior.Then,by using the method of graph embedding,three types of network are respectively embedded into low-dimensional vectors to obtain the characterization vectors of nodes.Finally,these characterization vectors are used to make a hybrid recommendation.The datasets in this paper are derived from the Country Hotel Reservation System in Guizhou Province.The experimental results show that,compared with traditional recommendation algorithms,the comprehensive evaluation index(F1)of the HRGE is improved by 20% and the Mean Average Precision(MAP)is increased by 11%.展开更多
Finding crucial vertices is a key problem for improving the reliability and ensuring the effective operation of networks,solved by approaches based on multiple attribute decision that suffer from ignoring the correlat...Finding crucial vertices is a key problem for improving the reliability and ensuring the effective operation of networks,solved by approaches based on multiple attribute decision that suffer from ignoring the correlation among each attribute or the heterogeneity between attribute and structure. To overcome these problems, a novel vertex centrality approach, called VCJG, is proposed based on joint nonnegative matrix factorization and graph embedding. The potential attributes with linearly independent and the structure information are captured automatically in light of nonnegative matrix factorization for factorizing the weighted adjacent matrix and the structure matrix, which is generated by graph embedding. And the smoothness strategy is applied to eliminate the heterogeneity between attributes and structure by joint nonnegative matrix factorization. Then VCJG integrates the above steps to formulate an overall objective function, and obtain the ultimately potential attributes fused the structure information of network through optimizing the objective function. Finally, the attributes are combined with neighborhood rules to evaluate vertex's importance. Through comparative analyses with experiments on nine real-world networks, we demonstrate that the proposed approach outperforms nine state-of-the-art algorithms for identification of vital vertices with respect to correlation, monotonicity and accuracy of top-10 vertices ranking.展开更多
Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabe...Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples well.Existing approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.展开更多
Heterogeneous graphs contain multiple types of entities and relations,which are capable of modeling complex interactions.Embedding on heterogeneous graphs has become an essential tool for analyzing and understanding s...Heterogeneous graphs contain multiple types of entities and relations,which are capable of modeling complex interactions.Embedding on heterogeneous graphs has become an essential tool for analyzing and understanding such graphs.Although these meticulously designed methods make progress,they are limited by model design and computational resources,making it difficult to scale to large-scale heterogeneous graph data and hindering the application and promotion of these methods.In this paper,we propose Restage,a relation structure-aware hierarchical heterogeneous graph embedding framework.Under this framework,embedding only a smaller-scale graph with existing graph representation learning methods is sufficient to obtain node representations on the original heterogeneous graph.We consider two types of relation structures in heterogeneous graphs:interaction relations and affiliation relations.Firstly,we design a relation structure-aware coarsening method to successively coarsen the original graph to the top-level layer,resulting in a smaller-scale graph.Secondly,we allow any unsupervised representation learning methods to obtain node embeddings on the top-level graph.Finally,we design a relation structure-aware refinement method to successively refine the node embeddings from the top-level graph back to the original graph,obtaining node embeddings on the original graph.Experimental results on three public heterogeneous graph datasets demonstrate the enhanced scalability of representation learning methods by the proposed Restage.On another large-scale graph,the speed of existing representation learning methods is increased by up to eighteen times at most.展开更多
Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parame...Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parameters are usually stored in a centralized manner.Centralized federated learning is easy to implement;however,a centralized scheme causes a communication bottleneck at the central server,which may significantly slow down the training process.To improve training efficiency,we investigate the decentralized federated learning scheme.The decentralized scheme has become feasible with the rapid development of device-to-device communication techniques under 5G.Nevertheless,the convergence rate of learning models in the decentralized scheme depends on the network topology design.We propose optimizing the topology design to improve training efficiency for decentralized federated learning,which is a non-trivial problem,especially when considering data heterogeneity.In this paper,we first demonstrate the advantage of hypercube topology and present a hypercube graph construction method to reduce data heterogeneity by carefully selecting neighbors of each training device—a process that resembles classic graph embedding.In addition,we propose a heuristic method for generating torus graphs.Moreover,we have explored the communication patterns in hypercube topology and propose a sequential synchronization scheme to reduce communication cost during training.A batch synchronization scheme is presented to fine-tune the communication pattern for hypercube topology.Experiments on real-world datasets show that our proposed graph construction methods can accelerate the training process,and our sequential synchronization scheme can significantly reduce the overall communication traffic during training.展开更多
Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-...Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-term and long-term spatial collaborative relationships among support agents and positions from long spatial–temporal trajectories. While the existing methods excel at recognizing collaborative behaviors from short trajectories, they often struggle with long spatial–temporal trajectories. To address this challenge, this paper introduces a dynamic graph method to enhance flight deck operation recognition. First, spatial–temporal collaborative relationships are modeled as a dynamic graph. Second, a discretized and compressed method is proposed to assign values to the states of this dynamic graph. To extract features that represent diverse collaborative relationships among agents and account for the duration of these relationships, a biased random walk is then conducted. Subsequently, the Swin Transformer is employed to comprehend spatial–temporal collaborative relationships, and a fully connected layer is applied to deck operation recognition. Finally, to address the scarcity of real datasets, a simulation pipeline is introduced to generate deck operations in virtual flight deck scenarios. Experimental results on the simulation dataset demonstrate the superior performance of the proposed method.展开更多
With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to ...With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to mine their POIs.However,classical recommendation models,such as collaborative filtering,are not effective for structuring POI recommendations due to the sparseness of user check-ins.Furthermore,LBSN recommendations are distinct from other recommendation scenarios.With respect to user data,a user’s check-in record sequence requires rich social and geographic information.In this paper,we propose two different neural-network models,structural deep network Graph embedding Neural-network Recommendation system(SG-Neu Rec)and Deepwalk on Graph Neural-network Recommendation system(DG-Neu Rec)to improve POI recommendation.combined with embedding representation from social and geographical graph information(called SG-Neu Rec and DG-Neu Rec).Our model naturally combines the embedding representations of social and geographical graph information with user-POI interaction representation and captures the potential user-POI interactions under the framework of the neural network.Finally,we compare the performances of these two models and analyze the reasons for their differences.Results from comprehensive experiments on two real LBSNs datasets indicate the effective performance of our model.展开更多
Knowledge graph embedding, which maps the entities and relations into low-dimensional vector spaces, has demonstrated its effectiveness in many tasks such as link prediction and relation extraction. Typical methods in...Knowledge graph embedding, which maps the entities and relations into low-dimensional vector spaces, has demonstrated its effectiveness in many tasks such as link prediction and relation extraction. Typical methods include TransE, TransH, and TransR. All these methods map different relations into the vector space separately and the intrinsic correlations of these relations are ignored. It is obvious that there exist some correlations among relations because different relations may connect to a common entity. For example, the triples （Steve Jobs, PlaceOfBrith, California） and （Apple Inc., Location, California） share the same entity California as their tail entity. We analyze the embedded relation matrices learned by TransE/TransH/TransR, and find that the correlations of relations do exist and they are showed as low-rank structure over the embedded relation matrix. It is natural to ask whether we can leverage these correlations to learn better embeddings for the entities and relations in a knowledge graph. In this paper, we propose to learn the embedded relation matrix by decomposing it as a product of two low-dimensional matrices, for characterizing the low-rank structure. The proposed method, called TransCoRe （Translation-Based Method via Modeling the Correlations of Relations）, learns the embeddings of entities and relations with translation-based framework. Experimental results based on the benchmark datasets of WordNet and Freebase demonstrate that our method outperforms the typical baselines on link prediction and triple classification tasks.展开更多
Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meani...Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meanings of a polysemous entity share one embedding vector.This study aims to propose a polysemous embedding approach,named KG embedding under relational contexts(ContE for short),for missing link prediction.Design/methodology/approach:ContE models and infers different relationship patterns by considering the context of the relationship,which is implicit in the local neighborhood of the relationship.The forward and backward impacts of the relationship in ContE are mapped to two different embedding vectors,which represent the contextual information of the relationship.Then,according to the position of the entity,the entity’s polysemous representation is obtained by adding its static embedding vector to the corresponding context vector of the relationship.Findings:ContE is a fully expressive,that is,given any ground truth over the triples,there are embedding assignments to entities and relations that can precisely separate the true triples from false ones.ContE is capable of modeling four connectivity patterns such as symmetry,antisymmetry,inversion and composition.Research limitations:ContE needs to do a grid search to find best parameters to get best performance in practice,which is a time-consuming task.Sometimes,it requires longer entity vectors to get better performance than some other models.Practical implications:ContE is a bilinear model,which is a quite simple model that could be applied to large-scale KGs.By considering contexts of relations,ContE can distinguish the exact meaning of an entity in different triples so that when performing compositional reasoning,it is capable to infer the connectivity patterns of relations and achieves good performance on link prediction tasks.Originality/value:ContE considers the contexts of entities in terms of their positions in triples and the relationships they link to.It decomposes a relation vector into two vectors,namely,forward impact vector and backward impact vector in order to capture the relational contexts.ContE has the same low computational complexity as TransE.Therefore,it provides a new approach for contextualized knowledge graph embedding.展开更多
The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in tra...The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.展开更多
Knowledge graph representation has been a long standing goal of artificial intelligence. In this paper,we consider a method for knowledge graph embedding of hyper-relational data, which are commonly found in knowledge...Knowledge graph representation has been a long standing goal of artificial intelligence. In this paper,we consider a method for knowledge graph embedding of hyper-relational data, which are commonly found in knowledge graphs. Previous models such as Trans（E, H, R） and CTrans R are either insufficient for embedding hyper-relational data or focus on projecting an entity into multiple embeddings, which might not be effective for generalization nor accurately reflect real knowledge. To overcome these issues, we propose the novel model Trans HR, which transforms the hyper-relations in a pair of entities into an individual vector, serving as a translation between them. We experimentally evaluate our model on two typical tasks—link prediction and triple classification.The results demonstrate that Trans HR significantly outperforms Trans（E, H, R） and CTrans R, especially for hyperrelational data.展开更多
When training a large-scale knowledge graph embedding(KGE)model with multiple graphics processing units(GPUs),the partition-based method is necessary for parallel training.However,existing partition-based training met...When training a large-scale knowledge graph embedding(KGE)model with multiple graphics processing units(GPUs),the partition-based method is necessary for parallel training.However,existing partition-based training methods suffer from low GPU utilization and high input/output(IO)overhead between the memory and disk.For a high IO overhead between the disk and memory problem,we optimized the twice partitioning with fine-grained GPU scheduling to reduce the IO overhead between the CPU memory and disk.For low GPU utilization caused by the GPU load imbalance problem,we proposed balanced partitioning and dynamic scheduling methods to accelerate the training speed in different cases.With the above methods,we proposed fine-grained partitioning KGE,an efficient KGE training framework with multiple GPUs.We conducted experiments on some benchmarks of the knowledge graph,and the results show that our method achieves speedup compared to existing framework on the training of KGE.展开更多
Network function virtualization （NFV） is a newly proposed technique designed to construct and manage network fimctions dynamically and efficiently. Allocating physical resources to the virtual network function forwa...Network function virtualization （NFV） is a newly proposed technique designed to construct and manage network fimctions dynamically and efficiently. Allocating physical resources to the virtual network function forwarding graph is a critical issue in NFV. We formulate the forwarding graph embedding （FGE） problem as a binary integer programming problem, which aims to increase the revenue and decrease the cost to a service provider （SP） while considering limited network resources and the requirements of virtual functions. We then design a novel regional resource clustering metric to quantify the embedding potential of each substrate node and propose a topology-aware FGE algorithm called ＇regional resource clustering FGE＇ （RRC-FGE）. After implementing our algorithms in C＋＋, simulation results showed that the total revenue was increased by more than 50 units and the acceptance ratio by more than 15%, and the cost of the service provider was decreased by more than 60 units.展开更多
Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the k...Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the knowledge graph increases exponentially with the depth of the tree,whereas the distances of nodes in Euclidean space are second-order polynomial distances,whereby knowledge embedding using graph neural networks in Euclidean space will not represent the distances between nodes well.This paper introduces a novel approach called hyperbolic hierarchical graph attention network(H2GAT)to rectify this limitation.Firstly,the paper conducts knowledge representation in the hyperbolic space,effectively mitigating the issue of exponential growth of nodes with tree depth and consequent information loss.Secondly,it introduces a hierarchical graph atten-tion mechanism specifically designed for the hyperbolic space,allowing for enhanced capture of the network structure inherent in the knowledge graph.Finally,the efficacy of the proposed H2GAT model is evaluated on benchmark datasets,namely WN18RR and FB15K-237,thereby validating its effectiveness.The H2GAT model achieved 0.445,0.515,and 0.586 in the Hits@1,Hits@3 and Hits@10 metrics respectively on the WN18RR dataset and 0.243,0.367 and 0.518 on the FB15K-237 dataset.By incorporating hyperbolic space embedding and hierarchical graph attention,the H2GAT model successfully addresses the limitations of existing hyperbolic knowledge embedding models,exhibiting its competence in knowledge graph completion tasks.展开更多
For graphs G and H,an embedding of G into H is an injection ϕ:V(G)→V(H)such that ϕ(a)ϕ(b)∈E(H)whenever ab∈E(G).A packing of p graphs G_(1),G_(2),…,G_(p) into H is a p-tupleΦ=(ϕ_(1),ϕ_(2),…,ϕ_(p))such that,for i=...For graphs G and H,an embedding of G into H is an injection ϕ:V(G)→V(H)such that ϕ(a)ϕ(b)∈E(H)whenever ab∈E(G).A packing of p graphs G_(1),G_(2),…,G_(p) into H is a p-tupleΦ=(ϕ_(1),ϕ_(2),…,ϕ_(p))such that,for i=1,2,…,p,ϕ_(i) is an embedding of Gi into H and the p sets ϕ_(i)(E(G_(i)))are mutually disjoint.Motivated by the"Tree Packing Conjecture"made by Gyar fas and Lehel,Wang Hong conjectured that for each k-partite tree,there is a packing of two copies of T(X)into a complete k-partite graph B_(n+m)(Y),where m=■k/2」..In this paper,we confirm this conjecture for k=4.展开更多
Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power system...Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power systems have explored KGs to develop intelligent dispatching systems for increasingly large power grids.With multiple power grid dispatching knowledge graphs(PDKGs)constructed by different agencies,the knowledge fusion of different PDKGs is useful for providing more accurate decision supports.To achieve this,entity alignment that aims at connecting different KGs by identifying equivalent entities is a critical step.Existing entity alignment methods cannot integrate useful structural,attribute,and relational information while calculating entities’similarities and are prone to making many-to-one alignments,thus can hardly achieve the best performance.To address these issues,this paper proposes a collective entity alignment model that integrates three kinds of available information and makes collective counterpart assignments.This model proposes a novel knowledge graph attention network(KGAT)to learn the embeddings of entities and relations explicitly and calculates entities’similarities by adaptively incorporating the structural,attribute,and relational similarities.Then,we formulate the counterpart assignment task as an integer programming(IP)problem to obtain one-to-one alignments.We not only conduct experiments on a pair of PDKGs but also evaluate o ur model on three commonly used cross-lingual KGs.Experimental comparisons indicate that our model outperforms other methods and provides an effective tool for the knowledge fusion of PDKGs.展开更多
The recommendation algorithm based on collaborative filtering is currently the most successful recommendation method. It recommends items to theuser based on the known historical interaction data of the target user. F...The recommendation algorithm based on collaborative filtering is currently the most successful recommendation method. It recommends items to theuser based on the known historical interaction data of the target user. Furthermore,the combination of the recommended algorithm based on collaborative filtrationand other auxiliary knowledge base is an effective way to improve the performance of the recommended system, of which the Co-Factorization Model(CoFM) is one representative research. CoFM, a fusion recommendation modelcombining the collaborative filtering model FM and the graph embeddingmodel TransE, introduces the information of many entities and their relationsin the knowledge graph into the recommendation system as effective auxiliaryinformation. It can effectively improve the accuracy of recommendations andalleviate the problem of sparse user historical interaction data. Unfortunately,the graph-embedded model TransE used in the CoFM model cannot solve the1-N, N-1, and N-N problems well. To tackle this problem, a novel fusion recommendation model Joint Factorization Machines and TransH Model (JFMH) isproposed, which improves CoFM by replacing the TransE model with TransHmodel. A large number of experiments on two widely used benchmark data setsshow that compared with CoFM, JFMH has improved performance in terms ofitem recommendation and knowledge graph completion, and is more competitivethan multiple baseline methods.展开更多
To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge gra...To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.展开更多
基金supported by the National Science and Technology Council(NSTC),Taiwan,under Grants Numbers 112-2622-E-029-009 and 112-2221-E-029-019.
文摘In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.
基金Supported by the National Natural Science Foundation of China(No.62203390)the Science and Technology Project of China TobaccoZhejiang Industrial Co.,Ltd(No.ZJZY2022E004)。
文摘In the tobacco industry,insider employee attack is a thorny problem that is difficult to detect.To solve this issue,this paper proposes an insider threat detection method based on heterogeneous graph embedding.First,the interrelationships between logs are fully considered,and log entries are converted into heterogeneous graphs based on these relationships.Second,the heterogeneous graph embedding is adopted and each log entry is represented as a low-dimensional feature vector.Then,normal logs and malicious logs are classified into different clusters by clustering algorithm to identify malicious logs.Finally,the effectiveness and superiority of the method is verified through experiments on the CERT dataset.The experimental results show that this method has better performance compared to some baseline methods.
文摘In recent years,online reservation systems of country hotel have become increasingly popular in rural areas.How to accurately recommend the houses of country hotel to the users is an urgent problem to be solved.Aiming at the problem of cold start and data sparseness in recommendation,a Hybrid Recommendation method based on Graph Embedding(HRGE)is proposed.First,three types of network are built,including user-user network based on user tag,househouse network based on house tag,and user-user network based on user behavior.Then,by using the method of graph embedding,three types of network are respectively embedded into low-dimensional vectors to obtain the characterization vectors of nodes.Finally,these characterization vectors are used to make a hybrid recommendation.The datasets in this paper are derived from the Country Hotel Reservation System in Guizhou Province.The experimental results show that,compared with traditional recommendation algorithms,the comprehensive evaluation index(F1)of the HRGE is improved by 20% and the Mean Average Precision(MAP)is increased by 11%.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.62162040 and 11861045)。
文摘Finding crucial vertices is a key problem for improving the reliability and ensuring the effective operation of networks,solved by approaches based on multiple attribute decision that suffer from ignoring the correlation among each attribute or the heterogeneity between attribute and structure. To overcome these problems, a novel vertex centrality approach, called VCJG, is proposed based on joint nonnegative matrix factorization and graph embedding. The potential attributes with linearly independent and the structure information are captured automatically in light of nonnegative matrix factorization for factorizing the weighted adjacent matrix and the structure matrix, which is generated by graph embedding. And the smoothness strategy is applied to eliminate the heterogeneity between attributes and structure by joint nonnegative matrix factorization. Then VCJG integrates the above steps to formulate an overall objective function, and obtain the ultimately potential attributes fused the structure information of network through optimizing the objective function. Finally, the attributes are combined with neighborhood rules to evaluate vertex's importance. Through comparative analyses with experiments on nine real-world networks, we demonstrate that the proposed approach outperforms nine state-of-the-art algorithms for identification of vital vertices with respect to correlation, monotonicity and accuracy of top-10 vertices ranking.
基金supported in part by the Key-Area Research and Development Program of Guangdong Province (2020B010166006)the National Natural Science Foundation of China (61972102)+2 种基金the Guangzhou Science and Technology Plan Project (023A04J1729)the Science and Technology development fund (FDCT)Macao SAR (015/2020/AMJ)。
文摘Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples well.Existing approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.
基金supported by the National Natural Science Foundation of China(Nos.1876001,61602003,and 61673020)the National High Technology Research and Development Program(No.2017YFB1401903)the Provincial Natural Science Foundation of Anhui Province(No.1708085QF156).
文摘Heterogeneous graphs contain multiple types of entities and relations,which are capable of modeling complex interactions.Embedding on heterogeneous graphs has become an essential tool for analyzing and understanding such graphs.Although these meticulously designed methods make progress,they are limited by model design and computational resources,making it difficult to scale to large-scale heterogeneous graph data and hindering the application and promotion of these methods.In this paper,we propose Restage,a relation structure-aware hierarchical heterogeneous graph embedding framework.Under this framework,embedding only a smaller-scale graph with existing graph representation learning methods is sufficient to obtain node representations on the original heterogeneous graph.We consider two types of relation structures in heterogeneous graphs:interaction relations and affiliation relations.Firstly,we design a relation structure-aware coarsening method to successively coarsen the original graph to the top-level layer,resulting in a smaller-scale graph.Secondly,we allow any unsupervised representation learning methods to obtain node embeddings on the top-level graph.Finally,we design a relation structure-aware refinement method to successively refine the node embeddings from the top-level graph back to the original graph,obtaining node embeddings on the original graph.Experimental results on three public heterogeneous graph datasets demonstrate the enhanced scalability of representation learning methods by the proposed Restage.On another large-scale graph,the speed of existing representation learning methods is increased by up to eighteen times at most.
基金This work was supported in part by the National Science Foundation(NSF)(Nos.SaTC 2310298,CNS 2214940,CPS 2128378,CNS 2107014,CNS 2150152,CNS 1824440,CNS 1828363,and CNS 1757533).
文摘Federated learning has been widely employed in many applications to protect the data privacy of participating clients.Although the dataset is decentralized among training devices in federated learning,the model parameters are usually stored in a centralized manner.Centralized federated learning is easy to implement;however,a centralized scheme causes a communication bottleneck at the central server,which may significantly slow down the training process.To improve training efficiency,we investigate the decentralized federated learning scheme.The decentralized scheme has become feasible with the rapid development of device-to-device communication techniques under 5G.Nevertheless,the convergence rate of learning models in the decentralized scheme depends on the network topology design.We propose optimizing the topology design to improve training efficiency for decentralized federated learning,which is a non-trivial problem,especially when considering data heterogeneity.In this paper,we first demonstrate the advantage of hypercube topology and present a hypercube graph construction method to reduce data heterogeneity by carefully selecting neighbors of each training device—a process that resembles classic graph embedding.In addition,we propose a heuristic method for generating torus graphs.Moreover,we have explored the communication patterns in hypercube topology and propose a sequential synchronization scheme to reduce communication cost during training.A batch synchronization scheme is presented to fine-tune the communication pattern for hypercube topology.Experiments on real-world datasets show that our proposed graph construction methods can accelerate the training process,and our sequential synchronization scheme can significantly reduce the overall communication traffic during training.
基金co-supported by the National Key Research and Development Program of China(No. 2021YFB3301504)the National Natural Science Foundation of China (Nos. 62072415, 62036010, 42301526, 62372416 and 62472389)the National Natural Science Foundation of Henan Province, China (No. 242300421215)
文摘Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-term and long-term spatial collaborative relationships among support agents and positions from long spatial–temporal trajectories. While the existing methods excel at recognizing collaborative behaviors from short trajectories, they often struggle with long spatial–temporal trajectories. To address this challenge, this paper introduces a dynamic graph method to enhance flight deck operation recognition. First, spatial–temporal collaborative relationships are modeled as a dynamic graph. Second, a discretized and compressed method is proposed to assign values to the states of this dynamic graph. To extract features that represent diverse collaborative relationships among agents and account for the duration of these relationships, a biased random walk is then conducted. Subsequently, the Swin Transformer is employed to comprehend spatial–temporal collaborative relationships, and a fully connected layer is applied to deck operation recognition. Finally, to address the scarcity of real datasets, a simulation pipeline is introduced to generate deck operations in virtual flight deck scenarios. Experimental results on the simulation dataset demonstrate the superior performance of the proposed method.
文摘With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to mine their POIs.However,classical recommendation models,such as collaborative filtering,are not effective for structuring POI recommendations due to the sparseness of user check-ins.Furthermore,LBSN recommendations are distinct from other recommendation scenarios.With respect to user data,a user’s check-in record sequence requires rich social and geographic information.In this paper,we propose two different neural-network models,structural deep network Graph embedding Neural-network Recommendation system(SG-Neu Rec)and Deepwalk on Graph Neural-network Recommendation system(DG-Neu Rec)to improve POI recommendation.combined with embedding representation from social and geographical graph information(called SG-Neu Rec and DG-Neu Rec).Our model naturally combines the embedding representations of social and geographical graph information with user-POI interaction representation and captures the potential user-POI interactions under the framework of the neural network.Finally,we compare the performances of these two models and analyze the reasons for their differences.Results from comprehensive experiments on two real LBSNs datasets indicate the effective performance of our model.
基金This work was supported by the National Basic Research 973 Program of China under Grant No. 2014CB340405, the National Key Research and Development Program of China under Grant No. 2016YFB1000902, and the National Natural Science Foundation of China under Grant Nos. 61402442, 61272177, 61173008, 61232010, 61303244, 61572469, 91646120 and 61572473.
文摘Knowledge graph embedding, which maps the entities and relations into low-dimensional vector spaces, has demonstrated its effectiveness in many tasks such as link prediction and relation extraction. Typical methods include TransE, TransH, and TransR. All these methods map different relations into the vector space separately and the intrinsic correlations of these relations are ignored. It is obvious that there exist some correlations among relations because different relations may connect to a common entity. For example, the triples （Steve Jobs, PlaceOfBrith, California） and （Apple Inc., Location, California） share the same entity California as their tail entity. We analyze the embedded relation matrices learned by TransE/TransH/TransR, and find that the correlations of relations do exist and they are showed as low-rank structure over the embedded relation matrix. It is natural to ask whether we can leverage these correlations to learn better embeddings for the entities and relations in a knowledge graph. In this paper, we propose to learn the embedded relation matrix by decomposing it as a product of two low-dimensional matrices, for characterizing the low-rank structure. The proposed method, called TransCoRe （Translation-Based Method via Modeling the Correlations of Relations）, learns the embeddings of entities and relations with translation-based framework. Experimental results based on the benchmark datasets of WordNet and Freebase demonstrate that our method outperforms the typical baselines on link prediction and triple classification tasks.
基金supported by the Key R&D Program Project of Zhejiang Province under Grant no.2019 C01004 and 2021C02004.
文摘Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meanings of a polysemous entity share one embedding vector.This study aims to propose a polysemous embedding approach,named KG embedding under relational contexts(ContE for short),for missing link prediction.Design/methodology/approach:ContE models and infers different relationship patterns by considering the context of the relationship,which is implicit in the local neighborhood of the relationship.The forward and backward impacts of the relationship in ContE are mapped to two different embedding vectors,which represent the contextual information of the relationship.Then,according to the position of the entity,the entity’s polysemous representation is obtained by adding its static embedding vector to the corresponding context vector of the relationship.Findings:ContE is a fully expressive,that is,given any ground truth over the triples,there are embedding assignments to entities and relations that can precisely separate the true triples from false ones.ContE is capable of modeling four connectivity patterns such as symmetry,antisymmetry,inversion and composition.Research limitations:ContE needs to do a grid search to find best parameters to get best performance in practice,which is a time-consuming task.Sometimes,it requires longer entity vectors to get better performance than some other models.Practical implications:ContE is a bilinear model,which is a quite simple model that could be applied to large-scale KGs.By considering contexts of relations,ContE can distinguish the exact meaning of an entity in different triples so that when performing compositional reasoning,it is capable to infer the connectivity patterns of relations and achieves good performance on link prediction tasks.Originality/value:ContE considers the contexts of entities in terms of their positions in triples and the relationships they link to.It decomposes a relation vector into two vectors,namely,forward impact vector and backward impact vector in order to capture the relational contexts.ContE has the same low computational complexity as TransE.Therefore,it provides a new approach for contextualized knowledge graph embedding.
基金supported by the National Science Foundation of USA(Nos.1829674,1912753,1704287,and 2011845)。
文摘The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph,which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics,as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only brings benefit for public health,disaster response,commercial promotion,and many other applications,but also gives birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links,while persevering sufficient non-sensitive information,such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.
基金partially supported by the National Natural Science Foundation of China(Nos.61302077,61520106007,61421061,and 61602048)
文摘Knowledge graph representation has been a long standing goal of artificial intelligence. In this paper,we consider a method for knowledge graph embedding of hyper-relational data, which are commonly found in knowledge graphs. Previous models such as Trans（E, H, R） and CTrans R are either insufficient for embedding hyper-relational data or focus on projecting an entity into multiple embeddings, which might not be effective for generalization nor accurately reflect real knowledge. To overcome these issues, we propose the novel model Trans HR, which transforms the hyper-relations in a pair of entities into an individual vector, serving as a translation between them. We experimentally evaluate our model on two typical tasks—link prediction and triple classification.The results demonstrate that Trans HR significantly outperforms Trans（E, H, R） and CTrans R, especially for hyperrelational data.
文摘When training a large-scale knowledge graph embedding(KGE)model with multiple graphics processing units(GPUs),the partition-based method is necessary for parallel training.However,existing partition-based training methods suffer from low GPU utilization and high input/output(IO)overhead between the memory and disk.For a high IO overhead between the disk and memory problem,we optimized the twice partitioning with fine-grained GPU scheduling to reduce the IO overhead between the CPU memory and disk.For low GPU utilization caused by the GPU load imbalance problem,we proposed balanced partitioning and dynamic scheduling methods to accelerate the training speed in different cases.With the above methods,we proposed fine-grained partitioning KGE,an efficient KGE training framework with multiple GPUs.We conducted experiments on some benchmarks of the knowledge graph,and the results show that our method achieves speedup compared to existing framework on the training of KGE.
基金Project supported by the National Natural Science Foundation of China （Nos. 61309020 and 61521003）
文摘Network function virtualization （NFV） is a newly proposed technique designed to construct and manage network fimctions dynamically and efficiently. Allocating physical resources to the virtual network function forwarding graph is a critical issue in NFV. We formulate the forwarding graph embedding （FGE） problem as a binary integer programming problem, which aims to increase the revenue and decrease the cost to a service provider （SP） while considering limited network resources and the requirements of virtual functions. We then design a novel regional resource clustering metric to quantify the embedding potential of each substrate node and propose a topology-aware FGE algorithm called ＇regional resource clustering FGE＇ （RRC-FGE）. After implementing our algorithms in C＋＋, simulation results showed that the total revenue was increased by more than 50 units and the acceptance ratio by more than 15%, and the cost of the service provider was decreased by more than 60 units.
基金the Beijing Municipal Science and Technology Program(No.Z231100001323004).
文摘Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC)has become an important research area in knowledge graph completion.However,the number of nodes in the knowledge graph increases exponentially with the depth of the tree,whereas the distances of nodes in Euclidean space are second-order polynomial distances,whereby knowledge embedding using graph neural networks in Euclidean space will not represent the distances between nodes well.This paper introduces a novel approach called hyperbolic hierarchical graph attention network(H2GAT)to rectify this limitation.Firstly,the paper conducts knowledge representation in the hyperbolic space,effectively mitigating the issue of exponential growth of nodes with tree depth and consequent information loss.Secondly,it introduces a hierarchical graph atten-tion mechanism specifically designed for the hyperbolic space,allowing for enhanced capture of the network structure inherent in the knowledge graph.Finally,the efficacy of the proposed H2GAT model is evaluated on benchmark datasets,namely WN18RR and FB15K-237,thereby validating its effectiveness.The H2GAT model achieved 0.445,0.515,and 0.586 in the Hits@1,Hits@3 and Hits@10 metrics respectively on the WN18RR dataset and 0.243,0.367 and 0.518 on the FB15K-237 dataset.By incorporating hyperbolic space embedding and hierarchical graph attention,the H2GAT model successfully addresses the limitations of existing hyperbolic knowledge embedding models,exhibiting its competence in knowledge graph completion tasks.
基金Supported by the National Natural Science Foundation of China(12071334)。
文摘For graphs G and H,an embedding of G into H is an injection ϕ:V(G)→V(H)such that ϕ(a)ϕ(b)∈E(H)whenever ab∈E(G).A packing of p graphs G_(1),G_(2),…,G_(p) into H is a p-tupleΦ=(ϕ_(1),ϕ_(2),…,ϕ_(p))such that,for i=1,2,…,p,ϕ_(i) is an embedding of Gi into H and the p sets ϕ_(i)(E(G_(i)))are mutually disjoint.Motivated by the"Tree Packing Conjecture"made by Gyar fas and Lehel,Wang Hong conjectured that for each k-partite tree,there is a packing of two copies of T(X)into a complete k-partite graph B_(n+m)(Y),where m=■k/2」..In this paper,we confirm this conjecture for k=4.
基金supported by the National Key R&D Program of China(2018AAA0101502)the Science and Technology Project of SGCC(State Grid Corporation of China):Fundamental Theory of Human-in-the-Loop Hybrid-Augmented Intelligence for Power Grid Dispatch and Control。
文摘Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power systems have explored KGs to develop intelligent dispatching systems for increasingly large power grids.With multiple power grid dispatching knowledge graphs(PDKGs)constructed by different agencies,the knowledge fusion of different PDKGs is useful for providing more accurate decision supports.To achieve this,entity alignment that aims at connecting different KGs by identifying equivalent entities is a critical step.Existing entity alignment methods cannot integrate useful structural,attribute,and relational information while calculating entities’similarities and are prone to making many-to-one alignments,thus can hardly achieve the best performance.To address these issues,this paper proposes a collective entity alignment model that integrates three kinds of available information and makes collective counterpart assignments.This model proposes a novel knowledge graph attention network(KGAT)to learn the embeddings of entities and relations explicitly and calculates entities’similarities by adaptively incorporating the structural,attribute,and relational similarities.Then,we formulate the counterpart assignment task as an integer programming(IP)problem to obtain one-to-one alignments.We not only conduct experiments on a pair of PDKGs but also evaluate o ur model on three commonly used cross-lingual KGs.Experimental comparisons indicate that our model outperforms other methods and provides an effective tool for the knowledge fusion of PDKGs.
基金funded by State Grid Shandong Electric Power Company Science and Technology Project Funding under Grant no.520613200001,520613180002,62061318C002Weihai Scientific Research and Innovation Fund(2020).
文摘The recommendation algorithm based on collaborative filtering is currently the most successful recommendation method. It recommends items to theuser based on the known historical interaction data of the target user. Furthermore,the combination of the recommended algorithm based on collaborative filtrationand other auxiliary knowledge base is an effective way to improve the performance of the recommended system, of which the Co-Factorization Model(CoFM) is one representative research. CoFM, a fusion recommendation modelcombining the collaborative filtering model FM and the graph embeddingmodel TransE, introduces the information of many entities and their relationsin the knowledge graph into the recommendation system as effective auxiliaryinformation. It can effectively improve the accuracy of recommendations andalleviate the problem of sparse user historical interaction data. Unfortunately,the graph-embedded model TransE used in the CoFM model cannot solve the1-N, N-1, and N-N problems well. To tackle this problem, a novel fusion recommendation model Joint Factorization Machines and TransH Model (JFMH) isproposed, which improves CoFM by replacing the TransE model with TransHmodel. A large number of experiments on two widely used benchmark data setsshow that compared with CoFM, JFMH has improved performance in terms ofitem recommendation and knowledge graph completion, and is more competitivethan multiple baseline methods.
基金Supported by the National Natural Science Foundation of China(No.61876144)。
文摘To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the superiority of convolutional neural networks(CNNs)in extracting semantic features of triple embeddings.However,these researches use only one single-shaped filter and fail to extract semantic features of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18 RR,and the better MR on dataset FB15k-237.
