Software security analysts typically only have access to the executable program and cannot directly access the source code of the program.This poses significant challenges to security analysis.While it is crucial to i...Software security analysts typically only have access to the executable program and cannot directly access the source code of the program.This poses significant challenges to security analysis.While it is crucial to identify vulnerabilities in such non-source code programs,there exists a limited set of generalized tools due to the low versatility of current vulnerability mining methods.However,these tools suffer from some shortcomings.In terms of targeted fuzzing,the path searching for target points is not streamlined enough,and the completely random testing leads to an excessively large search space.Additionally,when it comes to code similarity analysis,there are issues with incomplete code feature extraction,which may result in information loss.In this paper,we propose a cross-platform and cross-architecture approach to exploit vulnerabilities using neural network obfuscation techniques.By leveraging the Angr framework,a deobfuscation technique is introduced,along with the adoption of a VEX-IR-based intermediate language conversion method.This combination allows for the unified handling of binary programs across various architectures,compilers,and compilation options.Subsequently,binary programs are processed to extract multi-level spatial features using a combination of a skip-gram model with self-attention mechanism and a bidirectional Long Short-Term Memory(LSTM)network.Finally,the graph embedding network is utilized to evaluate the similarity of program functionalities.Based on these similarity scores,a target function is determined,and symbolic execution is applied to solve the target function.The solved content serves as the initial seed for targeted fuzzing.The binary program is processed by using the de-obfuscation technique and intermediate language transformation method,and then the similarity of program functions is evaluated by using a graph embedding network,and symbolic execution is performed based on these similarity scores.This approach facilitates cross-architecture analysis of executable programs without their source codes and concurrently reduces the risk of symbolic execution path explosion.展开更多
Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(C...Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.展开更多
Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the stru...Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks(HINs)into low-dimensional embeddings;this task is called heterogeneous network embedding(HNE).Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification,recommender systems,and information retrieval.Here,we provide a comprehensive survey of key advancements in the area of HNE.First,we define an encoder-decoder-based HNE model taxonomy.Then,we systematically overview,compare,and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks.We also summarize the application fields,benchmark datasets,open source tools,andperformance evaluation in theHNEarea.Finally,wediscuss open issues and suggest promising future directions.We anticipate that this survey will provide deep insights into research in the field of HNE.展开更多
For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most ...For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes.However,numerous real-world networks are naturally composed of multiple layers with different relation types;such a network is called a multiplex network.The majority of existing multiplex network embedding methods either overlook node attributes,resort to node labels for training,or underutilize underlying information shared across multiple layers.In this paper,we propose Multiplex Network Infomax(MNI),an unsupervised embedding framework to represent information of multiple layers into a unified embedding space.To be more specific,we aim to maximize the mutual information between the unified embedding and node embeddings of each layer.On the basis of this framework,we present an unsupervised network embedding method for attributed multiplex networks.Experimental results show that our method achieves competitive performance on not only node-related tasks,such as node classification,clustering,and similarity search,but also a typical edge-related task,i.e.,link prediction,at times even outperforming relevant supervised methods,despite that MNI is fully unsupervised.展开更多
Role-based network embedding aims to embed role-similar nodes into a similar embedding space,which is widely used in graph mining tasks such as role classification and detection.Roles are sets of nodes in graph networ...Role-based network embedding aims to embed role-similar nodes into a similar embedding space,which is widely used in graph mining tasks such as role classification and detection.Roles are sets of nodes in graph networks with similar structural patterns and functions.However,the rolesimilar nodes may be far away or even disconnected from each other.Meanwhile,the neighborhood node features and noise also affect the result of the role-based network embedding,which are also challenges of current network embedding work.In this paper,we propose a Role-based network Embedding via Quantum walk with weighted Features fusion(REQF),which simultaneously considers the influence of global and local role information,node features,and noise.Firstly,we capture the global role information of nodes via quantum walk based on its superposition property which emphasizes the local role information via biased quantum walk.Secondly,we utilize the quantum walkweighted characteristic function to extract and fuse features of nodes and their neighborhood by different distributions which contain role information implicitly.Finally,we leverage the Variational Auto-Encoder(VAE)to reduce the effect of noise.We conduct extensive experiments on seven real-world datasets,and the results show that REQF is more effective at capturing role information in the network,which outperforms the best baseline by up to 14.6% in role classification,and 23% in role detection on average.展开更多
The pursuit of the higher performance mobile communications forces the emergence of the fifth generation mobile communication(5G). 5G network, integrating wireless and wired domain, can be qualified for the complex vi...The pursuit of the higher performance mobile communications forces the emergence of the fifth generation mobile communication(5G). 5G network, integrating wireless and wired domain, can be qualified for the complex virtual network work oriented to the cross-domain requirement. In this paper, we focus on the multi-domain virtual network embedding in a heterogeneous 5G network infrastructure, which facilitates the resource sharing for diverse-function demands from fixed/mobile end users. We proposed the mathematical ILP model for this problem.And based on the layered-substrate-resource auxiliary graph and an effective six-quadrant service-type-judgment method, 5G embedding demands can be classified accurately to match different user access densities. A collection of novel heuristic algorithms of virtual 5G network embedding are proposed. A great deal of numerical simulation results testified that our algorithm performed better in terms of average blocking rate, routing latency and wireless/wired resource utilization, compared with the benchmark.展开更多
Network virtualization(NV) is pushed forward by its proponents as a crucial attribute of next generation network, aiming at overcoming the gradual ossification of current networks, particularly to the worldwide Intern...Network virtualization(NV) is pushed forward by its proponents as a crucial attribute of next generation network, aiming at overcoming the gradual ossification of current networks, particularly to the worldwide Internet. Through virtualization, multiple customized virtual networks(VNs), requested by users, are allowed to coexist on the underlying substrate networks(SNs). In addition, the virtualization scheme contributes to sharing underlying physical resources simultaneously and seamlessly. However, multiple technical issues still stand in the way of NV successful implementation. One key technical issue is virtual network embedding(VNE), known as the resource allocation problem for NV. This paper conducts a survey of embedding algorithms for VNE problem. At first, the NV business model for VNE problem is presented. Then, the latest VNE problem description is presented. Main performance metrics for evaluating embedding algorithms are also involved. Afterwards, existing VNE algorithms are detailed, according to the novel proposed category approach. Next, key future research aspects of embedding algorithms are listed out. Finally, the paper is briefly concluded.展开更多
Network virtualization(NV)is a highprofile way to solve the ossification problem of the nowadays Internet,and be able to support the diversified network naturally.In NV,Virtual Network Embedding(VNE)problem has been w...Network virtualization(NV)is a highprofile way to solve the ossification problem of the nowadays Internet,and be able to support the diversified network naturally.In NV,Virtual Network Embedding(VNE)problem has been widely considered as a crucial issue,which is aimed to embed Virtual Networks(VNs)onto the shared substrate networks(SNs)efficiently.Recently,some VNE approaches have developed Node Ranking strategies to drive and enhance the embedding efficiency.Node Ranking Strategy rank/sort the nodes according to the attributes of the node,including both residual local attributes(CPU,Bandwidth,storage,Etc.)and the global topology attributes(Number of neighborhood Nodes,Delay to other nodes,Etc.).This paper presents an overview of Node Ranking Strategies in Virtual Network Embedding,and possible directions of VNE Node Ranking Strategy.展开更多
Purpose: The goal of this study is to explore whether deep learning based embed ded models can provide a better visualization solution for large citation networks. De sign/methodology/approach: Our team compared the v...Purpose: The goal of this study is to explore whether deep learning based embed ded models can provide a better visualization solution for large citation networks. De sign/methodology/approach: Our team compared the visualization approach borrowed from the deep learning community with the well-known bibliometric network visualization for large scale data. 47,294 highly cited papers were visualized by using three network embedding models plus the t-SNE dimensionality reduction technique. Besides, three base maps were created with the same dataset for evaluation purposes. All base maps used the classic Open Ord method with different edge cutting strategies and parameters. Findings: The network embedded maps with t-SNE preserve a very similar global structure to the full edges classic force-directed map, while the maps vary in local structure. Among them, the Node2Vec model has the best overall visualization performance, the local structure has been significantly improved and the maps' layout has very high stability.Research limitations: The computational and time costs of training are very high for network em bedded models to obtain high dimensional latent vector. Only one dimensionality reduction technique was tested. Practical implications: This paper demonstrates that the network embedding models are able to accurately reconstruct the large bibliometric network in the vector space. In the future, apart from network visualization, many classical vector-based machine learning algorithms can be applied to network representations for solving bibliomet ric analysis tasks. Originality/value: This paper provides the first systematic comparison of classical science mapping visualization with network embedding based visualization on a large scale dataset. We showed deep learning based network embedding model with t-SNE can provide a richer,more stable science map. We also designed a practical evaluation method to investigate and compare maps.展开更多
Network virtualization is known as a promising technology to tackle the ossification of current Internet and will play an important role in the future network area. Virtual network embedding(VNE) is a key issue in net...Network virtualization is known as a promising technology to tackle the ossification of current Internet and will play an important role in the future network area. Virtual network embedding(VNE) is a key issue in network virtualization. VNE is NP-hard and former VNE algorithms are mostly heuristic in the literature.VNE exact algorithms have been developed in recent years. However, the constraints of exact VNE are only node capacity and link bandwidth.Based on these, this paper presents an exact VNE algorithm, ILP-LC, which is based on Integer Linear Programming(ILP), for embedding virtual network request with location constraints. This novel algorithm is aiming at mapping virtual network request(VNR) successfully as many as possible and consuming less substrate resources.The topology of each VNR is randomly generated by Waxman model. Simulation results show that the proposed ILP-LC algorithm outperforms the typical heuristic algorithms in terms of the VNR acceptance ratio, at least 15%.展开更多
Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator...Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.Design/methodology/approach:We propose an academic collaborator recommendation model based on attributed network embedding(ACR-ANE),which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes.The non-local neighbors for scholars are defined to capture strong relationships among scholars.A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.Findings:1.The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors.2.It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.Research limitations:The designed method works for static networks,without taking account of the network dynamics.Practical implications:The designed model is embedded in academic collaboration network structure and scholarly attributes,which can be used to help scholars recommend potential collaborators.Originality/value:Experiments on two real-world scholarly datasets,Aminer and APS,show that our proposed method performs better than other baselines.展开更多
The evolution of airborne tactical networks(ATNs)is impeded by the network ossification problem.As a solution,network virtualization(NV)can provide a flexible and scalable architecture where virtual network embedding(...The evolution of airborne tactical networks(ATNs)is impeded by the network ossification problem.As a solution,network virtualization(NV)can provide a flexible and scalable architecture where virtual network embedding(VNE)is a key part.However,existing VNE algorithms cannot be optimally adopted in the virtualization of ATN due to the complex interference in aircombat field.In this context,a highly reliable VNE algorithm based on the transmission rate for ATN virtualization(TR-ATVNE)is proposed to adapt well to the specific electromagnetic environment of ATN.Our algorithm coordinates node and link mapping.In the node mapping,transmission-rate resource is firstly defined to effectively evaluate the ranking value of substrate nodes under the interference of both environmental noises and enemy attacks.Meanwhile,a feasible splitting rule is proposed for path splitting in the link mapping,considering the interference between wireless links.Simulation results reveal that our algorithm is able to improve the acceptance ratio of virtual network requests while maintaining a high revenue-to-cost ratio under the complex electromagnetic interference.展开更多
In recent years,satellite networks have been proposed as an essential part of next-generation mobile communication systems.Software defined networking techniques are introduced in satellite networks to handle the grow...In recent years,satellite networks have been proposed as an essential part of next-generation mobile communication systems.Software defined networking techniques are introduced in satellite networks to handle the growing challenges induced by time-varying topology,intermittent inter-satellite link and dramatically increased satellite constellation size.This survey covers the latest progress of software defined satellite networks,including key techniques,existing solutions,challenges,opportunities,and simulation tools.To the best of our knowledge,this paper is the most comprehensive survey that covers the latest progress of software defined satellite networks.An open GitHub repository is further created where the latest papers on this topic will be tracked and updated periodically.Compared with these existing surveys,this survey contributes from three aspects:(1)an up-to-date SDN-oriented review for the latest progress of key techniques and solutions in software defined satellite networks;(2)an inspiring summary of existing challenges,new research opportunities and publicly available simulation tools for follow-up studies;(3)an effort of building a public repository to track new results.展开更多
Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do ...Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do not pay attention to the multi-interaction between nodes,which limits the extraction and mining of potential deep interactions between nodes.To tackle the problem,we propose a method called Multi-Interaction heterogeneous information Network Embedding(MINE).Firstly,we introduced the multi-interactions heterogeneous information network and extracted complex heterogeneous relation sequences by the multi-interaction extraction algorithm.Secondly,we use a well-designed multi-relationship network fusion model based on the attention mechanism to fuse multiple interactional relationships.Finally,applying a multitasking model makes the learned vector contain richer semantic relationships.A large number of practical experiments prove that our proposed method outperforms existing methods on multiple data sets.展开更多
Network analysis is a promisingfield in the area of network applications as different types of traffic grow enormously and exponentially.Reliable route prediction is a challenging task in the Large Scale Networks(LSN).V...Network analysis is a promisingfield in the area of network applications as different types of traffic grow enormously and exponentially.Reliable route prediction is a challenging task in the Large Scale Networks(LSN).Various non-self-learning and self-learning approaches have been adopted to predict reliable routing.Routing protocols decide how to send all the packets from source to the destination addresses across the network through their IP.In the current era,dynamic protocols are preferred as they network self-learning internally using an algorithm and may not entail being updated physically more than the static protocols.A novel method named Reliable Route Prediction Model(RRPM)is proposed tofind the best routes in the given hefty gage network to balance the load of the entire network to advance the network recital.The task is carried out in two phases.In thefirst phase,Network Embedding(NE)based node classification is carried out.The second phase involves the network analysis to predict the route of the LSN.The experiment is carried out for average data transmission and rerouting time is measured between RRPM and Routing Information Protocol(RIP)protocol models with before and after failure links.It was observed that average transmission time for RIP protocol has measured as 18.5 ms and RRPM protocol has measured as 18.2 ms.Hence the proposed RRPM model outperforms well than the traditional routefinding protocols such as RIP and Open Shortest Path First(OSPF).展开更多
Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link prediction.Unfortunately,existing network e...Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link prediction.Unfortunately,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream tasks.To achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ex-amples.However,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial training.In this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving regularization.We formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original node.Extensive experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.展开更多
In power systems,failures of vulnerable lines can trigger large-scale cascading failures,and vulnerability assessment is dedicated to locating these lines and reducing the risks of such failures.Based on a structure a...In power systems,failures of vulnerable lines can trigger large-scale cascading failures,and vulnerability assessment is dedicated to locating these lines and reducing the risks of such failures.Based on a structure and attribute network embedding(SANE)algorithm,a novel quantitative vulnerability analysis method is proposed to identify vulnerable lines in this research.First,a two-layered random walk network with topological and electrical properties of transmission lines is established.Subsequently,based on the weighted degree of nodes in the two-layered network,the inter-layer and intra-layer walking transition probabilities are developed to obtain walk sequences.Then,a Word2Vec algorithm is applied to obtain lowdimension vectors representing transmission lines,according to obtained walk sequences for calculating the vulnerability index of transmissions lines.Finally,the proposed method is compared with three widely used methods in two test systems.Results show the network embedding based method is superior to those comparison methods and can provide guidance for identifying vulnerable lines.展开更多
In this paper,we address the problem of unsuperised social network embedding,which aims to embed network nodes,including node attributes,into a latent low dimensional space.In recent methods,the fusion mechanism of no...In this paper,we address the problem of unsuperised social network embedding,which aims to embed network nodes,including node attributes,into a latent low dimensional space.In recent methods,the fusion mechanism of node attributes and network structure has been proposed for the problem and achieved impressive prediction performance.However,the non-linear property of node attributes and network structure is not efficiently fused in existing methods,which is potentially helpful in learning a better network embedding.To this end,in this paper,we propose a novel model called ASM(Adaptive Specific Mapping)based on encoder-decoder framework.In encoder,we use the kernel mapping to capture the non-linear property of both node attributes and network structure.In particular,we adopt two feature mapping functions,namely an untrainable function for node attributes and a trainable function for network structure.By the mapping functions,we obtain the low dimensional feature vectors for node attributes and network structure,respectively.Then,we design an attention layer to combine the learning of both feature vectors and adaptively learn the node embedding.In encoder,we adopt the component of reconstruction for the training process of learning node attributes and network structure.We conducted a set of experiments on seven real-world social network datasets.The experimental results verify the effectiveness and efficiency of our method in comparison with state-of-the-art baselines.展开更多
Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. ...Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.展开更多
This paper aims to effectively solve the problem of the influence maximization in social networks.For this purpose,an influence maximization method that can identify influential nodes via the community structure and t...This paper aims to effectively solve the problem of the influence maximization in social networks.For this purpose,an influence maximization method that can identify influential nodes via the community structure and the influence distribution difference is proposed.Firstly,the network embedding-based community detection approach is developed,by which the social network is divided into several high-quality communities.Secondly,the solution of influence maximization is composed of the candidate stage and the greedy stage.The candidate stage is to select candidate nodes from the interior and the boundary of each community using a heuristic algorithm,and the greedy stage is to determine seed nodes with the largest marginal influence increment from the candidate set through the sub-modular property-based Greedy algorithm.Finally,experimental results demonstrate the superiority of the proposed method compared with existing methods,from which one can further find that our work can achieve a good tradeoff between the influence spread and the running time.展开更多
文摘Software security analysts typically only have access to the executable program and cannot directly access the source code of the program.This poses significant challenges to security analysis.While it is crucial to identify vulnerabilities in such non-source code programs,there exists a limited set of generalized tools due to the low versatility of current vulnerability mining methods.However,these tools suffer from some shortcomings.In terms of targeted fuzzing,the path searching for target points is not streamlined enough,and the completely random testing leads to an excessively large search space.Additionally,when it comes to code similarity analysis,there are issues with incomplete code feature extraction,which may result in information loss.In this paper,we propose a cross-platform and cross-architecture approach to exploit vulnerabilities using neural network obfuscation techniques.By leveraging the Angr framework,a deobfuscation technique is introduced,along with the adoption of a VEX-IR-based intermediate language conversion method.This combination allows for the unified handling of binary programs across various architectures,compilers,and compilation options.Subsequently,binary programs are processed to extract multi-level spatial features using a combination of a skip-gram model with self-attention mechanism and a bidirectional Long Short-Term Memory(LSTM)network.Finally,the graph embedding network is utilized to evaluate the similarity of program functionalities.Based on these similarity scores,a target function is determined,and symbolic execution is applied to solve the target function.The solved content serves as the initial seed for targeted fuzzing.The binary program is processed by using the de-obfuscation technique and intermediate language transformation method,and then the similarity of program functions is evaluated by using a graph embedding network,and symbolic execution is performed based on these similarity scores.This approach facilitates cross-architecture analysis of executable programs without their source codes and concurrently reduces the risk of symbolic execution path explosion.
基金supported in part by the National Natural Science Foundation of China (62272078)the CAAI-Huawei MindSpore Open Fund (CAAIXSJLJJ-2021-035A)the Doctoral Student Talent Training Program of Chongqing University of Posts and Telecommunications (BYJS202009)。
文摘Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.
基金supported by the National Key Research and Development Plan of China(2017YFB0503700,2016YFB0501801)the National Natural Science Foundation of China(61170026,62173157)+1 种基金the Thirteen Five-Year Research Planning Project of National Language Committee(No.YB135-149)the Fundamental Research Funds for the Central Universities(Nos.CCNU20QN022,CCNU20QN021,CCNU20ZT012).
文摘Real-world complex networks are inherently heterogeneous;they have different types of nodes,attributes,and relationships.In recent years,various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks(HINs)into low-dimensional embeddings;this task is called heterogeneous network embedding(HNE).Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification,recommender systems,and information retrieval.Here,we provide a comprehensive survey of key advancements in the area of HNE.First,we define an encoder-decoder-based HNE model taxonomy.Then,we systematically overview,compare,and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks.We also summarize the application fields,benchmark datasets,open source tools,andperformance evaluation in theHNEarea.Finally,wediscuss open issues and suggest promising future directions.We anticipate that this survey will provide deep insights into research in the field of HNE.
基金This work was supported by the National Natural Science Foundation of China(NSFC)under Grant U19B2004in part by National Key R&D Program of China under Grant 2022YFB2901202+1 种基金in part by the Open Funding Projects of the State Key Laboratory of Communication Content Cognition(No.20K05 and No.A02107)in part by the Special Fund for Science and Technology of Guangdong Province under Grant 2019SDR002.
文摘For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes.However,numerous real-world networks are naturally composed of multiple layers with different relation types;such a network is called a multiplex network.The majority of existing multiplex network embedding methods either overlook node attributes,resort to node labels for training,or underutilize underlying information shared across multiple layers.In this paper,we propose Multiplex Network Infomax(MNI),an unsupervised embedding framework to represent information of multiple layers into a unified embedding space.To be more specific,we aim to maximize the mutual information between the unified embedding and node embeddings of each layer.On the basis of this framework,we present an unsupervised network embedding method for attributed multiplex networks.Experimental results show that our method achieves competitive performance on not only node-related tasks,such as node classification,clustering,and similarity search,but also a typical edge-related task,i.e.,link prediction,at times even outperforming relevant supervised methods,despite that MNI is fully unsupervised.
基金supported in part by the National Nature Science Foundation of China(Grant 62172065)the Natural Science Foundation of Chongqing(Grant cstc2020jcyjmsxmX0137).
文摘Role-based network embedding aims to embed role-similar nodes into a similar embedding space,which is widely used in graph mining tasks such as role classification and detection.Roles are sets of nodes in graph networks with similar structural patterns and functions.However,the rolesimilar nodes may be far away or even disconnected from each other.Meanwhile,the neighborhood node features and noise also affect the result of the role-based network embedding,which are also challenges of current network embedding work.In this paper,we propose a Role-based network Embedding via Quantum walk with weighted Features fusion(REQF),which simultaneously considers the influence of global and local role information,node features,and noise.Firstly,we capture the global role information of nodes via quantum walk based on its superposition property which emphasizes the local role information via biased quantum walk.Secondly,we utilize the quantum walkweighted characteristic function to extract and fuse features of nodes and their neighborhood by different distributions which contain role information implicitly.Finally,we leverage the Variational Auto-Encoder(VAE)to reduce the effect of noise.We conduct extensive experiments on seven real-world datasets,and the results show that REQF is more effective at capturing role information in the network,which outperforms the best baseline by up to 14.6% in role classification,and 23% in role detection on average.
基金supported in part by Open Foundation of State Key Laboratory of Information Photonics and Optical Communications (Grant No. IPOC2014B009)Fundamental Research Funds for the Central Universities (Grant Nos. N130817002, N150401002)+1 种基金Foundation of the Education Department of Liaoning Province (Grant No. L2014089)National Natural Science Foundation of China (Grant Nos. 61302070, 61401082, 61471109, 61502075, 91438110)
文摘The pursuit of the higher performance mobile communications forces the emergence of the fifth generation mobile communication(5G). 5G network, integrating wireless and wired domain, can be qualified for the complex virtual network work oriented to the cross-domain requirement. In this paper, we focus on the multi-domain virtual network embedding in a heterogeneous 5G network infrastructure, which facilitates the resource sharing for diverse-function demands from fixed/mobile end users. We proposed the mathematical ILP model for this problem.And based on the layered-substrate-resource auxiliary graph and an effective six-quadrant service-type-judgment method, 5G embedding demands can be classified accurately to match different user access densities. A collection of novel heuristic algorithms of virtual 5G network embedding are proposed. A great deal of numerical simulation results testified that our algorithm performed better in terms of average blocking rate, routing latency and wireless/wired resource utilization, compared with the benchmark.
基金supported by the National Key Research and Development of China under Grant 2018YFC1314903the National Natural Science Foundation of China under Grant 61372124 and Grant 61427801
文摘Network virtualization(NV) is pushed forward by its proponents as a crucial attribute of next generation network, aiming at overcoming the gradual ossification of current networks, particularly to the worldwide Internet. Through virtualization, multiple customized virtual networks(VNs), requested by users, are allowed to coexist on the underlying substrate networks(SNs). In addition, the virtualization scheme contributes to sharing underlying physical resources simultaneously and seamlessly. However, multiple technical issues still stand in the way of NV successful implementation. One key technical issue is virtual network embedding(VNE), known as the resource allocation problem for NV. This paper conducts a survey of embedding algorithms for VNE problem. At first, the NV business model for VNE problem is presented. Then, the latest VNE problem description is presented. Main performance metrics for evaluating embedding algorithms are also involved. Afterwards, existing VNE algorithms are detailed, according to the novel proposed category approach. Next, key future research aspects of embedding algorithms are listed out. Finally, the paper is briefly concluded.
基金The authors would like to thank the reviewers for their detailed reviews and constructive comments,which have helped improve the quality of this paper.This work was supported by National Science Foundation of China under Grants 6187144。
文摘Network virtualization(NV)is a highprofile way to solve the ossification problem of the nowadays Internet,and be able to support the diversified network naturally.In NV,Virtual Network Embedding(VNE)problem has been widely considered as a crucial issue,which is aimed to embed Virtual Networks(VNs)onto the shared substrate networks(SNs)efficiently.Recently,some VNE approaches have developed Node Ranking strategies to drive and enhance the embedding efficiency.Node Ranking Strategy rank/sort the nodes according to the attributes of the node,including both residual local attributes(CPU,Bandwidth,storage,Etc.)and the global topology attributes(Number of neighborhood Nodes,Delay to other nodes,Etc.).This paper presents an overview of Node Ranking Strategies in Virtual Network Embedding,and possible directions of VNE Node Ranking Strategy.
基金funded by the strategic research project of the Development Planning Bureau of the Chinese Academy of Sciences under Grant No.GHJ-ZLZX-2019-42the Youth Fund Project of Institutes of Science and Development, Chinese Academy of Sciences under Grant name “Research on Key Methods in Comparison of Scientific Funding Layout”。
文摘Purpose: The goal of this study is to explore whether deep learning based embed ded models can provide a better visualization solution for large citation networks. De sign/methodology/approach: Our team compared the visualization approach borrowed from the deep learning community with the well-known bibliometric network visualization for large scale data. 47,294 highly cited papers were visualized by using three network embedding models plus the t-SNE dimensionality reduction technique. Besides, three base maps were created with the same dataset for evaluation purposes. All base maps used the classic Open Ord method with different edge cutting strategies and parameters. Findings: The network embedded maps with t-SNE preserve a very similar global structure to the full edges classic force-directed map, while the maps vary in local structure. Among them, the Node2Vec model has the best overall visualization performance, the local structure has been significantly improved and the maps' layout has very high stability.Research limitations: The computational and time costs of training are very high for network em bedded models to obtain high dimensional latent vector. Only one dimensionality reduction technique was tested. Practical implications: This paper demonstrates that the network embedding models are able to accurately reconstruct the large bibliometric network in the vector space. In the future, apart from network visualization, many classical vector-based machine learning algorithms can be applied to network representations for solving bibliomet ric analysis tasks. Originality/value: This paper provides the first systematic comparison of classical science mapping visualization with network embedding based visualization on a large scale dataset. We showed deep learning based network embedding model with t-SNE can provide a richer,more stable science map. We also designed a practical evaluation method to investigate and compare maps.
基金supported by the National Basic Research Program of China(973 Program)under Grant 2013CB329005
文摘Network virtualization is known as a promising technology to tackle the ossification of current Internet and will play an important role in the future network area. Virtual network embedding(VNE) is a key issue in network virtualization. VNE is NP-hard and former VNE algorithms are mostly heuristic in the literature.VNE exact algorithms have been developed in recent years. However, the constraints of exact VNE are only node capacity and link bandwidth.Based on these, this paper presents an exact VNE algorithm, ILP-LC, which is based on Integer Linear Programming(ILP), for embedding virtual network request with location constraints. This novel algorithm is aiming at mapping virtual network request(VNR) successfully as many as possible and consuming less substrate resources.The topology of each VNR is randomly generated by Waxman model. Simulation results show that the proposed ILP-LC algorithm outperforms the typical heuristic algorithms in terms of the VNR acceptance ratio, at least 15%.
基金supported by National Natural Science Foundation of China(No.61603310)the Fundamental Research Funds for the Central Universities(No.XDJK2018B019).
文摘Purpose:Based on real-world academic data,this study aims to use network embedding technology to mining academic relationships,and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.Design/methodology/approach:We propose an academic collaborator recommendation model based on attributed network embedding(ACR-ANE),which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes.The non-local neighbors for scholars are defined to capture strong relationships among scholars.A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.Findings:1.The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors.2.It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.Research limitations:The designed method works for static networks,without taking account of the network dynamics.Practical implications:The designed model is embedded in academic collaboration network structure and scholarly attributes,which can be used to help scholars recommend potential collaborators.Originality/value:Experiments on two real-world scholarly datasets,Aminer and APS,show that our proposed method performs better than other baselines.
基金supported by the National Natural Science Foundation of China(61701521)the Shaanxi Provincial Natural Science Foundation(2018JQ6074)。
文摘The evolution of airborne tactical networks(ATNs)is impeded by the network ossification problem.As a solution,network virtualization(NV)can provide a flexible and scalable architecture where virtual network embedding(VNE)is a key part.However,existing VNE algorithms cannot be optimally adopted in the virtualization of ATN due to the complex interference in aircombat field.In this context,a highly reliable VNE algorithm based on the transmission rate for ATN virtualization(TR-ATVNE)is proposed to adapt well to the specific electromagnetic environment of ATN.Our algorithm coordinates node and link mapping.In the node mapping,transmission-rate resource is firstly defined to effectively evaluate the ranking value of substrate nodes under the interference of both environmental noises and enemy attacks.Meanwhile,a feasible splitting rule is proposed for path splitting in the link mapping,considering the interference between wireless links.Simulation results reveal that our algorithm is able to improve the acceptance ratio of virtual network requests while maintaining a high revenue-to-cost ratio under the complex electromagnetic interference.
基金This work is supported by the Fundamental Research Funds for the Central Universities.
文摘In recent years,satellite networks have been proposed as an essential part of next-generation mobile communication systems.Software defined networking techniques are introduced in satellite networks to handle the growing challenges induced by time-varying topology,intermittent inter-satellite link and dramatically increased satellite constellation size.This survey covers the latest progress of software defined satellite networks,including key techniques,existing solutions,challenges,opportunities,and simulation tools.To the best of our knowledge,this paper is the most comprehensive survey that covers the latest progress of software defined satellite networks.An open GitHub repository is further created where the latest papers on this topic will be tracked and updated periodically.Compared with these existing surveys,this survey contributes from three aspects:(1)an up-to-date SDN-oriented review for the latest progress of key techniques and solutions in software defined satellite networks;(2)an inspiring summary of existing challenges,new research opportunities and publicly available simulation tools for follow-up studies;(3)an effort of building a public repository to track new results.
基金This work is supported by the Fundamental Research Funds for the Central Universities(Grant No.HIT.NSRIF.201714)Weihai Science and Technology Development Program(2016DXGJMS15)Key Research and Development Program in Shandong Provincial(2017GGX90103).
文摘Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do not pay attention to the multi-interaction between nodes,which limits the extraction and mining of potential deep interactions between nodes.To tackle the problem,we propose a method called Multi-Interaction heterogeneous information Network Embedding(MINE).Firstly,we introduced the multi-interactions heterogeneous information network and extracted complex heterogeneous relation sequences by the multi-interaction extraction algorithm.Secondly,we use a well-designed multi-relationship network fusion model based on the attention mechanism to fuse multiple interactional relationships.Finally,applying a multitasking model makes the learned vector contain richer semantic relationships.A large number of practical experiments prove that our proposed method outperforms existing methods on multiple data sets.
文摘Network analysis is a promisingfield in the area of network applications as different types of traffic grow enormously and exponentially.Reliable route prediction is a challenging task in the Large Scale Networks(LSN).Various non-self-learning and self-learning approaches have been adopted to predict reliable routing.Routing protocols decide how to send all the packets from source to the destination addresses across the network through their IP.In the current era,dynamic protocols are preferred as they network self-learning internally using an algorithm and may not entail being updated physically more than the static protocols.A novel method named Reliable Route Prediction Model(RRPM)is proposed tofind the best routes in the given hefty gage network to balance the load of the entire network to advance the network recital.The task is carried out in two phases.In thefirst phase,Network Embedding(NE)based node classification is carried out.The second phase involves the network analysis to predict the route of the LSN.The experiment is carried out for average data transmission and rerouting time is measured between RRPM and Routing Information Protocol(RIP)protocol models with before and after failure links.It was observed that average transmission time for RIP protocol has measured as 18.5 ms and RRPM protocol has measured as 18.2 ms.Hence the proposed RRPM model outperforms well than the traditional routefinding protocols such as RIP and Open Shortest Path First(OSPF).
基金This work was supported by the National Natural Science Foundation of China under Grant Nos.U21B2046 and 62102402the National Key Research and Development Program of China under Grant No.2020AAA0105200.
文摘Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link prediction.Unfortunately,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream tasks.To achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ex-amples.However,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial training.In this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving regularization.We formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original node.Extensive experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.
基金supported in part by the National Natural Science Foundation of China(51977082)Guangdong Basic and Applied Basic Research Foundation(2021A1515110675)the Project funded by China Postdoctoral Science Foundation(2021M701239)。
文摘In power systems,failures of vulnerable lines can trigger large-scale cascading failures,and vulnerability assessment is dedicated to locating these lines and reducing the risks of such failures.Based on a structure and attribute network embedding(SANE)algorithm,a novel quantitative vulnerability analysis method is proposed to identify vulnerable lines in this research.First,a two-layered random walk network with topological and electrical properties of transmission lines is established.Subsequently,based on the weighted degree of nodes in the two-layered network,the inter-layer and intra-layer walking transition probabilities are developed to obtain walk sequences.Then,a Word2Vec algorithm is applied to obtain lowdimension vectors representing transmission lines,according to obtained walk sequences for calculating the vulnerability index of transmissions lines.Finally,the proposed method is compared with three widely used methods in two test systems.Results show the network embedding based method is superior to those comparison methods and can provide guidance for identifying vulnerable lines.
基金supported by the National Natural Science Foundation of China(Grant Nos.61572537,U1501252).
文摘In this paper,we address the problem of unsuperised social network embedding,which aims to embed network nodes,including node attributes,into a latent low dimensional space.In recent methods,the fusion mechanism of node attributes and network structure has been proposed for the problem and achieved impressive prediction performance.However,the non-linear property of node attributes and network structure is not efficiently fused in existing methods,which is potentially helpful in learning a better network embedding.To this end,in this paper,we propose a novel model called ASM(Adaptive Specific Mapping)based on encoder-decoder framework.In encoder,we use the kernel mapping to capture the non-linear property of both node attributes and network structure.In particular,we adopt two feature mapping functions,namely an untrainable function for node attributes and a trainable function for network structure.By the mapping functions,we obtain the low dimensional feature vectors for node attributes and network structure,respectively.Then,we design an attention layer to combine the learning of both feature vectors and adaptively learn the node embedding.In encoder,we adopt the component of reconstruction for the training process of learning node attributes and network structure.We conducted a set of experiments on seven real-world social network datasets.The experimental results verify the effectiveness and efficiency of our method in comparison with state-of-the-art baselines.
文摘Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.
基金The authors are grateful to the anonymous reviewers and the editor for their valuable comments and suggestions.This work is supported by Natural Science Foundation of China(Grant Nos.61702066 and 11747125)Major Project of Science and Technology Research Program of Chongqing Education Commission of China(Grant No.KJZD-M201900601)+3 种基金Chongqing Research Program of Basic Research and Frontier Technology(Grant Nos.cstc2017jcyjAX0256 and cstc2018jcy-jAX0154)Project Supported by Chongqing Municipal Key Laboratory of Institutions of Higher Education(Grant No.cqupt-mct-201901)Tech-nology Foundation of Guizhou Province(QianKeHeJiChu[2020]1Y269)New academic seedling cultivation and exploration innovation project(QianKeHe Platform Talents[2017]5789-21).
文摘This paper aims to effectively solve the problem of the influence maximization in social networks.For this purpose,an influence maximization method that can identify influential nodes via the community structure and the influence distribution difference is proposed.Firstly,the network embedding-based community detection approach is developed,by which the social network is divided into several high-quality communities.Secondly,the solution of influence maximization is composed of the candidate stage and the greedy stage.The candidate stage is to select candidate nodes from the interior and the boundary of each community using a heuristic algorithm,and the greedy stage is to determine seed nodes with the largest marginal influence increment from the candidate set through the sub-modular property-based Greedy algorithm.Finally,experimental results demonstrate the superiority of the proposed method compared with existing methods,from which one can further find that our work can achieve a good tradeoff between the influence spread and the running time.