Network information mining is the study of the network topology,which may answer a large number of applicationbased questions towards the structural evolution and the function of a real system.The question can be rela...Network information mining is the study of the network topology,which may answer a large number of applicationbased questions towards the structural evolution and the function of a real system.The question can be related to how the real system evolves or how individuals interact with each other in social networks.Although the evolution of the real system may seem to be found regularly,capturing patterns on the whole process of evolution is not trivial.Link prediction is one of the most important technologies in network information mining,which can help us understand the evolution mechanism of real-life network.Link prediction aims to uncover missing links or quantify the likelihood of the emergence of nonexistent links from known network structures.Currently,widely existing methods of link prediction almost focus on short-path networks that usually have a myriad of close triangular structures.However,these algorithms on highly sparse or longpath networks have poor performance.Here,we propose a new index that is associated with the principles of structural equivalence and shortest path length(SESPL)to estimate the likelihood of link existence in long-path networks.Through a test of 548 real networks,we find that SESPL is more effective and efficient than other similarity-based predictors in long-path networks.Meanwhile,we also exploit the performance of SESPL predictor and of embedding-based approaches via machine learning techniques.The results show that the performance of SESPL can achieve a gain of 44.09%over GraphWave and 7.93%over Node2vec.Finally,according to the matrix of maximal information coefficient(MIC)between all the similarity-based predictors,SESPL is a new independent feature in the space of traditional similarity features.展开更多
Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack...Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.展开更多
Effective link analysis techniques are needed to help law enforcement and intelligence agencies fight money laundering. This paper presents a link analysis technique that uses a modified shortest-path algorithms to id...Effective link analysis techniques are needed to help law enforcement and intelligence agencies fight money laundering. This paper presents a link analysis technique that uses a modified shortest-path algorithms to identify the strongest association paths between entities in a money laundering network. Based on two-tree Dijkstra and Priority＇First-Search （PFS） algorithm, a modified algorithm is presented. To apply the algorithm, a network representation transformation is made first.展开更多
This paper is devoted to find an intelligent and safe path for two-link robotic arm in dynamic environment. This paper focuses on computational part of motion planning in completely changing dynamic environment at eve...This paper is devoted to find an intelligent and safe path for two-link robotic arm in dynamic environment. This paper focuses on computational part of motion planning in completely changing dynamic environment at every motion sample domains,?since the local minima and sharp edges are the most common problems in all path planning algorithms. In addition, finding a path solution in a dynamic environment represents a challenge for the robotics researchers,?so in this paper, a proposed mixing approach was suggested to overcome all these obstructions. The proposed approach methodology?for obtaining robot interactive path planning solution in known dynamic environment utilizes?the use of modified heuristic D-star (D*) algorithm based on the full free Cartesian space analysis at each motion sample with the Particle Swarm Optimization (PSO) technique.?Also, a modification on the?D* algorithm has been done to match the dynamic environment requirements by adding stop and return backward cases which is not included in the original D* algorithm theory. The resultant interactive path solution was computed by taking into consideration the time and position changes of the moving obstacles. Furthermore, to insure the enhancement of the?final path length optimality, the PSO technique was used.?The simulation results are given to show the effectiveness of the proposed method.展开更多
Missing link prediction provides significant instruction for both analysis of network structure and mining of unknown links in incomplete networks. Recently, many algorithms have been proposed based on various node-si...Missing link prediction provides significant instruction for both analysis of network structure and mining of unknown links in incomplete networks. Recently, many algorithms have been proposed based on various node-similarity measures. Among these measures, the common neighbour index, the resource allocation index, and the local path index, stemming from different source, have been proved to have relatively high accuracy and low computational effort. In this paper, we propose a similarity index by combining the resource allocation index and the local path index. Simulation results on six unweighted networks show that the accuracy of the proposed index is higher than that of the local path one. Based on the same idea of the present index, we develop its corresponding weighted version and test it on several weighted networks. It is found that, except for the USAir network, the weighted variant also performs better than both the weighted resource allocation index and the weighted local path index. Due to the improved accuracy and the still low computational complexity, the indices may be useful for link prediction.展开更多
Line-of-sight (LOS) link planning condition has been observed to have effects on the atmospheric factor which cause crucial signal loss. The main objective of the planning was to improve a set of a link using point to...Line-of-sight (LOS) link planning condition has been observed to have effects on the atmospheric factor which cause crucial signal loss. The main objective of the planning was to improve a set of a link using point to point condition to assist the performance in emerging its strategy for handling the fixed WLAN service. The purpose of this paper is to provide a quick description of various propagation loss mechanisms on Link Budget Tool (LBT). LBT is customized to create point to point link for local area network (LAN) through radio frequency range operating between 2.400 GHz and 5.800 GHz. This software is able to define the effect of signal loss and expected performances according to the distances between link propagation conditions based on a number of system parameters.展开更多
The natural language to SQL(NL2SQL)task is an emerging research area that aims to transform a natural language with a given database into an SQL query.The earlier approaches were to process the input into a heterogene...The natural language to SQL(NL2SQL)task is an emerging research area that aims to transform a natural language with a given database into an SQL query.The earlier approaches were to process the input into a heterogeneous graph.However,previous models failed to distinguish the types of multi-hop connections of the heterogeneous graph,which tended to ignore crucial semantic path information.To this end,a two-layer attention network is presented to focus on essential neighbor nodes and mine enlightening semantic paths for feature encoding.The weighted edge is introduced for schema linking to connect the nodes with semantic similarity.In the decoding phase,a rule-based pruning strategy is offered to refine the generated SQL queries.From the experimental results,the approach is shown to learn a good encoding representation and decode the representation to generate results with practical meaning.展开更多
In conventional shared risk link group （SRLG）-diverse path selection （CSPS） algorithm in survivable GMPLS networks, SRLG is taken into account when selecting the backup paths, while the primary path selection meth...In conventional shared risk link group （SRLG）-diverse path selection （CSPS） algorithm in survivable GMPLS networks, SRLG is taken into account when selecting the backup paths, while the primary path selection method is the sarne as the algorithms without SRLG constraint. A problem of CSPS algorithm is that, after a primary path is selected, the success probability to select an SRLG-diverse backup path for it is low. If SRLG is taken into account when computing the primary path, then the probability to successfully select an SRLG-diverse backup path will be much increased. Based on this idea, an active SRLG-diverse path selection （ASPS） algorithm is proposed. To actively avoid selecting those SRLG links, when computing the primary path, a link that share risk with more links is assigned a larger link cost. To improve the resource utilization ratio, it is permitted that the bandwidth resources are shared among backup paths. What is more, differentiated reliability （DiR） requirements of different customers are considered in ASPS algorithm. The simulation results show that, compared with CSPS algorithm, ASPS algorithm not only increases successful protection probability but also improves resource utilization ratio.展开更多
目的:基于专利引文网络探索类器官领域的技术发展主路径。方法:本研究通过构建类器官领域的专利引文网络,采用搜索路径连接数算法(search path link count,SPLC)计算遍历权重,对类器官领域开展主路径分析,探索该领域的技术发展轨迹。结...目的:基于专利引文网络探索类器官领域的技术发展主路径。方法:本研究通过构建类器官领域的专利引文网络,采用搜索路径连接数算法(search path link count,SPLC)计算遍历权重,对类器官领域开展主路径分析,探索该领域的技术发展轨迹。结果:类器官领域共有专利申请2 250项,包含专利引文12 722件;专利申请数量逐年增长,技术开发聚焦于疾病模型、药物筛选、细胞培养及器官芯片等方向。主路径分析显示,全局主路径上专利数量最多,有12件,包含1条技术路线,全局关键路径主路径与全局主路径一致;局部前向主路径上有10件专利,包含1条技术路线;这2条技术路线反映出中国类器官领域的技术发展轨迹,中国技术创新聚焦于基于肿瘤类器官技术的疾病机制研究、基于肺癌类器官模型的疾病机制研究、肺癌类器官模型的开发与优化。局部后向主路径上有9件专利,包含2条技术路线,局部关键路径主路径与局部后向主路径一致;这2条技术路线反映出美国类器官领域的技术发展轨迹,技术创新聚焦于胃肠道类器官培养与疾病模型研究、干细胞驱动的器官功能修复技术、细胞移植与器官再生。结论:本研究通过类器官领域的专利主路径分析,识别技术发展轨迹,从情报学角度为类器官研发提供信息支撑。展开更多
The education and management of party members is the basic and regular work of the party building, which is crucial to improving the quality of the party members and maintaining the advanced nature and purity of the p...The education and management of party members is the basic and regular work of the party building, which is crucial to improving the quality of the party members and maintaining the advanced nature and purity of the party members. College student Party members are an important part of Party members, and it is of great significance to do a good job in educating college student Party members. Based on the exploration of the weak links in the education process of college student party members, this paper puts forward targeted solutions to improve the pertinence and effectiveness of college student party members education.展开更多
传统的知识图谱表示学习模型主要聚焦于三元组内部的结构信息,而未能充分利用外部语义增强嵌入表征能力,如没有充分考虑实体间的多步关系路径信息以及不同路径的重要程度,且没有利用实体描述信息增强上下文感知能力。为提升知识图谱的...传统的知识图谱表示学习模型主要聚焦于三元组内部的结构信息,而未能充分利用外部语义增强嵌入表征能力,如没有充分考虑实体间的多步关系路径信息以及不同路径的重要程度,且没有利用实体描述信息增强上下文感知能力。为提升知识图谱的应用效果,提出融合多步关系路径和实体描述信息的知识图谱表示学习(MPDRL)模型。首先,对两实体间的路径信息进行编码,并使用自注意力机制计算路径权重,从而获得关系路径信息的表示;其次,使用BERT(Bidirectional Encoder Representations from Transformers)模型对实体描述信息进行编码,并利用双向注意力机制计算实体描述信息嵌入与三元组关系嵌入之间的注意力权重,从而增强实体的语义信息;最后,将关系路径信息嵌入、实体描述信息嵌入和三元组结构嵌入融合起来进行训练。为评估模型性能,在公开数据集上针对所提模型和基准模型进行链接预测和三元组分类的实验。结果表明:在链接预测任务中,与融合关系路径与实体描述信息的知识图谱表示学习方法(PDRL)、多跳关系路径模型Att-ConvBiLSTM以及融合实体描述与关系路径信息的知识图谱嵌入模型TPKGE相比,所提模型在FB15k-237数据集上的Hit@10指标分别提高了5.7、2.9、2.5个百分点;在三元组分类任务上,所提模型在FB15k-237和WN18RR数据集上的准确率较最优基准模型PDRL分别提升了2.81和0.90个百分点。展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.61773091 and 62173065)the Industry-University-Research Innovation Fund for Chinese Universities(Grant No.2021ALA03016)+2 种基金the Fund for University Innovation Research Group of Chongqing(Grant No.CXQT21005)the National Social Science Foundation of China(Grant No.20CTQ029)the Fundamental Research Funds for the Central Universities(Grant No.SWU119062).
文摘Network information mining is the study of the network topology,which may answer a large number of applicationbased questions towards the structural evolution and the function of a real system.The question can be related to how the real system evolves or how individuals interact with each other in social networks.Although the evolution of the real system may seem to be found regularly,capturing patterns on the whole process of evolution is not trivial.Link prediction is one of the most important technologies in network information mining,which can help us understand the evolution mechanism of real-life network.Link prediction aims to uncover missing links or quantify the likelihood of the emergence of nonexistent links from known network structures.Currently,widely existing methods of link prediction almost focus on short-path networks that usually have a myriad of close triangular structures.However,these algorithms on highly sparse or longpath networks have poor performance.Here,we propose a new index that is associated with the principles of structural equivalence and shortest path length(SESPL)to estimate the likelihood of link existence in long-path networks.Through a test of 548 real networks,we find that SESPL is more effective and efficient than other similarity-based predictors in long-path networks.Meanwhile,we also exploit the performance of SESPL predictor and of embedding-based approaches via machine learning techniques.The results show that the performance of SESPL can achieve a gain of 44.09%over GraphWave and 7.93%over Node2vec.Finally,according to the matrix of maximal information coefficient(MIC)between all the similarity-based predictors,SESPL is a new independent feature in the space of traditional similarity features.
基金Supported by the National Natural Science Foundation of China(No.61876144).
文摘Knowledge graph(KG) link prediction aims to address the problem of missing multiple valid triples in KGs. Existing approaches either struggle to efficiently model the message passing process of multi-hop paths or lack transparency of model prediction principles. In this paper,a new graph convolutional network path semantic-aware graph convolution network(PSGCN) is proposed to achieve modeling the semantic information of multi-hop paths. PSGCN first uses a random walk strategy to obtain all-hop paths in KGs,then captures the semantics of the paths by Word2Sec and long shortterm memory(LSTM) models,and finally converts them into a potential representation for the graph convolution network(GCN) messaging process. PSGCN combines path-based inference methods and graph neural networks to achieve better interpretability and scalability. In addition,to ensure the robustness of the model,the value of the path thresholdKis experimented on the FB15K-237 and WN18RR datasets,and the final results prove the effectiveness of the model.
基金Supported bythe National Tenth Five-Year PlanforScientific and Technological Development of China (2001BA102A06-11)
文摘Effective link analysis techniques are needed to help law enforcement and intelligence agencies fight money laundering. This paper presents a link analysis technique that uses a modified shortest-path algorithms to identify the strongest association paths between entities in a money laundering network. Based on two-tree Dijkstra and Priority＇First-Search （PFS） algorithm, a modified algorithm is presented. To apply the algorithm, a network representation transformation is made first.
文摘This paper is devoted to find an intelligent and safe path for two-link robotic arm in dynamic environment. This paper focuses on computational part of motion planning in completely changing dynamic environment at every motion sample domains,?since the local minima and sharp edges are the most common problems in all path planning algorithms. In addition, finding a path solution in a dynamic environment represents a challenge for the robotics researchers,?so in this paper, a proposed mixing approach was suggested to overcome all these obstructions. The proposed approach methodology?for obtaining robot interactive path planning solution in known dynamic environment utilizes?the use of modified heuristic D-star (D*) algorithm based on the full free Cartesian space analysis at each motion sample with the Particle Swarm Optimization (PSO) technique.?Also, a modification on the?D* algorithm has been done to match the dynamic environment requirements by adding stop and return backward cases which is not included in the original D* algorithm theory. The resultant interactive path solution was computed by taking into consideration the time and position changes of the moving obstacles. Furthermore, to insure the enhancement of the?final path length optimality, the PSO technique was used.?The simulation results are given to show the effectiveness of the proposed method.
基金Project supported by the National Natural Science Foundation of China (Grant No. 30570432)the Young Research Foundation of Education Department of Hunan Province of China (Grant No. 11B128)partly by the Doctor Startup Project of Xiangtan University (Grant No. 10QDZ20)
文摘Missing link prediction provides significant instruction for both analysis of network structure and mining of unknown links in incomplete networks. Recently, many algorithms have been proposed based on various node-similarity measures. Among these measures, the common neighbour index, the resource allocation index, and the local path index, stemming from different source, have been proved to have relatively high accuracy and low computational effort. In this paper, we propose a similarity index by combining the resource allocation index and the local path index. Simulation results on six unweighted networks show that the accuracy of the proposed index is higher than that of the local path one. Based on the same idea of the present index, we develop its corresponding weighted version and test it on several weighted networks. It is found that, except for the USAir network, the weighted variant also performs better than both the weighted resource allocation index and the weighted local path index. Due to the improved accuracy and the still low computational complexity, the indices may be useful for link prediction.
文摘Line-of-sight (LOS) link planning condition has been observed to have effects on the atmospheric factor which cause crucial signal loss. The main objective of the planning was to improve a set of a link using point to point condition to assist the performance in emerging its strategy for handling the fixed WLAN service. The purpose of this paper is to provide a quick description of various propagation loss mechanisms on Link Budget Tool (LBT). LBT is customized to create point to point link for local area network (LAN) through radio frequency range operating between 2.400 GHz and 5.800 GHz. This software is able to define the effect of signal loss and expected performances according to the distances between link propagation conditions based on a number of system parameters.
文摘The natural language to SQL(NL2SQL)task is an emerging research area that aims to transform a natural language with a given database into an SQL query.The earlier approaches were to process the input into a heterogeneous graph.However,previous models failed to distinguish the types of multi-hop connections of the heterogeneous graph,which tended to ignore crucial semantic path information.To this end,a two-layer attention network is presented to focus on essential neighbor nodes and mine enlightening semantic paths for feature encoding.The weighted edge is introduced for schema linking to connect the nodes with semantic similarity.In the decoding phase,a rule-based pruning strategy is offered to refine the generated SQL queries.From the experimental results,the approach is shown to learn a good encoding representation and decode the representation to generate results with practical meaning.
基金supported by the National Natural Science Foundation of China (60673142)Applied Basic ResearchProject of Sichuan Province (2006J13-067).
文摘In conventional shared risk link group （SRLG）-diverse path selection （CSPS） algorithm in survivable GMPLS networks, SRLG is taken into account when selecting the backup paths, while the primary path selection method is the sarne as the algorithms without SRLG constraint. A problem of CSPS algorithm is that, after a primary path is selected, the success probability to select an SRLG-diverse backup path for it is low. If SRLG is taken into account when computing the primary path, then the probability to successfully select an SRLG-diverse backup path will be much increased. Based on this idea, an active SRLG-diverse path selection （ASPS） algorithm is proposed. To actively avoid selecting those SRLG links, when computing the primary path, a link that share risk with more links is assigned a larger link cost. To improve the resource utilization ratio, it is permitted that the bandwidth resources are shared among backup paths. What is more, differentiated reliability （DiR） requirements of different customers are considered in ASPS algorithm. The simulation results show that, compared with CSPS algorithm, ASPS algorithm not only increases successful protection probability but also improves resource utilization ratio.
文摘The education and management of party members is the basic and regular work of the party building, which is crucial to improving the quality of the party members and maintaining the advanced nature and purity of the party members. College student Party members are an important part of Party members, and it is of great significance to do a good job in educating college student Party members. Based on the exploration of the weak links in the education process of college student party members, this paper puts forward targeted solutions to improve the pertinence and effectiveness of college student party members education.
文摘传统的知识图谱表示学习模型主要聚焦于三元组内部的结构信息,而未能充分利用外部语义增强嵌入表征能力,如没有充分考虑实体间的多步关系路径信息以及不同路径的重要程度,且没有利用实体描述信息增强上下文感知能力。为提升知识图谱的应用效果,提出融合多步关系路径和实体描述信息的知识图谱表示学习(MPDRL)模型。首先,对两实体间的路径信息进行编码,并使用自注意力机制计算路径权重,从而获得关系路径信息的表示;其次,使用BERT(Bidirectional Encoder Representations from Transformers)模型对实体描述信息进行编码,并利用双向注意力机制计算实体描述信息嵌入与三元组关系嵌入之间的注意力权重,从而增强实体的语义信息;最后,将关系路径信息嵌入、实体描述信息嵌入和三元组结构嵌入融合起来进行训练。为评估模型性能,在公开数据集上针对所提模型和基准模型进行链接预测和三元组分类的实验。结果表明:在链接预测任务中,与融合关系路径与实体描述信息的知识图谱表示学习方法(PDRL)、多跳关系路径模型Att-ConvBiLSTM以及融合实体描述与关系路径信息的知识图谱嵌入模型TPKGE相比,所提模型在FB15k-237数据集上的Hit@10指标分别提高了5.7、2.9、2.5个百分点;在三元组分类任务上,所提模型在FB15k-237和WN18RR数据集上的准确率较最优基准模型PDRL分别提升了2.81和0.90个百分点。
