The Evolving Bipartite Network and Semi-Bipartite Network Models with Adjustable Scale and Hybrid Attachment Mechanisms

The bipartite graph structure exists in the connections of many objects in the real world, and the evolving modeling is a good method to describe and understand the generation and evolution within various real complex networks. Previous bipartite models were proposed to mostly explain the principle of attachments, and ignored the diverse growth speed of nodes of sets in different bipartite networks. In this paper, we propose an evolving bipartite network model with adjustable node scale and hybrid attachment mechanisms, which uses different probability parameters to control the scale of two disjoint sets of nodes and the preference strength of hybrid attachment respectively. The results show that the degree distribution of single set in the proposed model follows a shifted power-law distribution when parameter r and s are not equal to 0, or exponential distribution when r or s is equal to 0. Furthermore, we extend the previous model to a semi-bipartite network model, which embeds more user association information into the internal network, so that the model is capable of carrying and revealing more deep information of each user in the network. The simulation results of two models are in good agreement with the empirical data, which verifies that the models have a good performance on real networks from the perspective of degree distribution. We believe these two models are valuable for an explanation of the origin and growth of bipartite systems that truly exist.

Mathematical Model and Algorithm for Link Community Detection in Bipartite Networks

In the past ten years, community detection in complex networks has attracted more and more attention of researchers. Communities often correspond to functional subunits in the complex systems. In complex network, a node community can be defined as a subgraph induced by a set of nodes, while a link community is a subgraph induced by a set of links. Although most researches pay more attention to identifying node communities in both unipartite and bipartite networks, some researchers have investigated the link community detection problem in unipartite networks. But current research pays little attention to the link community detection problem in bipartite networks. In this paper, we investigate the link community detection problem in bipartite networks, and formulate it into an integer programming model. We proposed a genetic algorithm for partition the bipartite network into overlapping link communities. Simulations are done on both artificial networks and real-world networks. The results show that the bipartite network can be efficiently partitioned into overlapping link communities by the genetic algorithm.

An MDL approach to efficiently discover communities in bipartite network

An minimum description length(MDL) criterion is proposed to choose a good partition for a bipartite network. A heuristic algorithm based on combination theory is presented to approach the optimal partition. As the heuristic algorithm automatically searches for the number of partitions, no user intervention is required. Finally, experiments are conducted on various datasets, and the results show that our method generates higher quality results than the state-of-art methods, cross-association and bipartite, recursively induced modules. Experiment results also show the good scalability of the proposed algorithm. The method is applied to traditional Chinese medicine(TCM) formula and Chinese herbal network whose community structure is not well known, and found that it detects significant and it is informative community division.

A uniform framework of projection and community detection for one-mode network in bipartite networks

Projection is a widely used method in bipartite networks. However, each projection has a specific application scenario and differs in the forms of mapping for bipartite networks. In this paper, inspired by the network-based information exchange dynamics, we propose a uniform framework of projection. Subsequently, an information exchange rate projection based on the nature of community structures of a network （named IERCP） is designed to detect community structures of bipartite networks. Results from the synthetic and real-world networks show that the IERCP algorithm has higher performance compared with the other projection methods. It suggests that the IERCP may extract more information hidden in bipartite networks and minimize information loss.

Predictive Characteristics of Co-authorship Networks: Comparing the Unweighted, Weighted, and Bipartite Cases

Purpose： This study aims to answer the question to what extent different types of networks can be used to predict future co-authorship among authors.Design/methodology/approach： We compare three types ot networks： unwelgntea networks, in which a link represents a past collaboration; weighted networks, in which links are weighted by the number of joint publications; and bipartite author-publication networks. The analysis investigates their relation to positive stability, as well as their potential in predicting links in future versions of the co-authorship network. Several hypotheses are tested.Findings： Among other results, we find that weighted networks do not automatically lead to better predictions. Bipartite networks, however, outperform unweighted networks in almost all cases. Research limitations： Only two relatively small case studies are considered Practical implications： The study suggests that future link prediction studies on networks should consider using the bipartite network as a training network. Originality/value： This is the first systematic comparison of unweighted, weighted, and bipartite training networks in link prediction.

Recommender System Combining Popularity and Novelty Based on One-Mode Projection of Weighted Bipartite Network

Personalized recommendation algorithms,which are effective means to solve information overload,are popular topics in current research.In this paper,a recommender system combining popularity and novelty(RSCPN)based on one-mode projection of weighted bipartite network is proposed.The edge between a user and item is weighted with the item’s rating,and we consider the difference in the ratings of different users for an item to obtain a reasonable method of measuring the similarity between users.RSCPN can be used in the same model for popularity and novelty recommendation by setting different parameter values and analyzing how a change in parameters affects the popularity and novelty of the recommender system.We verify and compare the accuracy,diversity and novelty of the proposed model with those of other models,and results show that RSCPN is feasible.

A Novel Recommendation Algorithm Integrates Resource Allocation and Resource Transfer in Weighted Bipartite Network

Grid-based recommendation algorithms view users and items as abstract nodes,and the information utilised by the algorithm is hidden in the selection relationships between users and items.Although these relationships can be easily handled,much useful information is overlooked,resulting in a less accurate recommendation algorithm.The aim of this paper is to propose improvements on the standard substance diffusion algorithm,taking into account the influence of the user’s rating on the recommended item,adding a moderating factor,and optimising the initial resource allocation vector and resource transfer matrix in the recommendation algorithm.An average ranking score evaluation index is introduced to quantify user satisfaction with the recommendation results.Experiments are conducted on the MovieLens training dataset,and the experimental results show that the proposed algorithm outperforms classical collaborative filtering systems and network structure based recommendation systems in terms of recommendation accuracy and hit rate.

智能电网中基于二分图匹配的网络切片资源分配算法

为了解决智能电网中多类业务的服务质量需求难以同时得到满足的问题并兼顾电力终端和网络侧经济效用,提出了一种基于二分图匹配的网络切片资源分配算法。针对智能电网场景中的控制类和采集类业务,为电力终端分别制定相应的投标信息,并据此计算支付价格和效用矩阵;将网络切片与电力终端之间的资源分配建模为二分图匹配问题,根据不同业务的时延、传输速率或能耗需求,向终端分配不同的切片资源以最大化系统效用。仿真结果表明,相较于已有的双向拍卖算法和贪心算法,所提算法能够提高10%~20%的系统效用。

网络视角下航空公司竞争态势及影响因素研究

为剖析疫情时期中国国内主要客运航空公司竞争格局和竞争优势的影响因素,利用TOPSIS-熵值法和修正Huff模型量化航空公司在航线上的竞争优势强度,构建基于优势强度的航空公司-航线赋权二分网络,从网络的视角对航空公司竞争优势市场划分及其静态特征进行研究,利用Tobit回归模型剖析竞争优势的影响因素。研究表明:在疫情时期航空公司多市场接触程度较低,三大航空公司竞争优势明显,其优势在城市分布上差异巨大,主要集中在其基地城市。HU、3U等航空公司在市场竞争中优势不明显,更多表现为竞争且主要围绕沿海二线城市展开;航空公司竞争优势受到多因素共同制约,疫情时期收益更多表示成本控制的能力,低成本航空公司9C相较HU、3C等航空公司更具优势。

一种融合表征的农产品推荐算法

针对农产品电商平台,产品季节性强、地域性强、用户行为多变,导致推荐效果不理想的问题,提出了一种融合表征的农产品推荐算法。首先,用长短期记忆网络和注意力网络相结合组成深度兴趣网络,以此来捕获物品的潜在特征;其次,构建用户-商品二部图;再次,利用图神经网络提取图数据的连接信息对每个节点的影响,并更新节点的嵌入式表示,以获取用户的潜在特征;最后,将两种潜在特征通过多层感知机得到待推荐农产品的购买概率,进一步提取和利用了用户行为序列中的用户深度兴趣,并将其融合深度兴趣网络进行推荐。实验结果表明:融合表征的农产品推荐算法相较于原有模型AUC指标提高9%以上,准确率和召回率提高约6%以上;相较于不考虑节点嵌入式表示的情况,AUC和准确率、召回率也均有提高。

保留模体信息的属性二分图神经网络表示学习

目前网络表示学习方法大多针对通过网络,忽略了属性二分网络的特殊性以及网络的模体信息等。为了解决以上问题,提出一种保留模体信息的属性二分图神经网络表示学习方法MABG。该方法首先通过网络中两节点共同参与形成的蝶形模体数量来调整边的权重,从而构建模体权重矩阵,获得包含模体信息的属性二分网络邻接矩阵。接着采取不同的策略捕捉网络中的显式和属性隐式消息,对于不同类型节点集合间的显式关系采用消息传递机制,对于同类型节点中的隐式关系采用消息对齐机制,同时使用对抗模型最小化输入特征和显式关系表示之间的差异,之后通过级联框架来捕捉高阶信息并得到最终的节点表示。将该模型在四个真实公开的数据集上执行推荐任务并与其他方法进行对比,验证了该模型的有效性。

基于汉字拆分嵌入和二部图的残损碑文识别

古籍碑刻承载着丰富的历史文化信息,但是由于自然风化浸蚀和人为破坏使得碑石上的文字信息残缺不全。古碑文语义信息多样化且样例不足,使得学习行文语义补全识别残损文字变得十分困难。该文试图从字形空间语义建模解决补全残损汉字进行识别理解这一挑战性任务。该文在层级拆分嵌入(HDE)编码方法的基础上使用动态图修补嵌入(DynamicGrape),对待识别汉字的图像进行特征映射并判别是否残损。如未残损直接转化为层级拆分编码,输入二部图推理字节点到部件节点的边权重,比对字库编码识别理解;如残损需要在字库里检索可能字和部件,对汉字编码的特征维度进行选择,输入二部图推理预测可能的汉字结果。在自建的数据集以及中文自然文本(CTW)数据集中进行验证,结果表明二部图网络可以有效迁移和推理出残损文字字形信息,该文方法可以有效对残损汉字进行识别理解,为残损结构信息处理开拓出了新的思路和途径。

基于二分网络加权投影的急性鼻咽炎中药配伍规律挖掘及组合用药预测

目的从二分网络加权投影角度挖掘中药方剂配伍规律,提出一种新的挖掘中药配伍规律的方法,并预测新型药物组合,为指导临床治疗急性鼻咽炎用药提供依据。方法以中医药综合数据库(TCMID)中的急性鼻咽炎方剂数据为数据源,通过提取方剂和药物构建二分网络,继而使用加权投影得到药物网络投影图,结合二分网络加权投影进行社会网络分析,基于皮尔逊相关性进行系统聚类的研究方法挖掘中药“君臣佐使”的配伍规律,并使用链路预测进行核心药物预测。结果二分网络加权投影与皮尔逊相关性进行系统聚类分析相结合的方式在中药方剂的配伍规律研究中作用显著。在链路预测中,选用11个链路预测指标,区分加权与无权算法后最终计算出的加权指标曲线下面积(AUC)大于无权指标,且在加权指标中,AUC最大指标为网络资源分配指标,预测出7组药物组合,包括白头翁与毛诃子、安息香与石椒草、白花茶与附子等。结论二分网络加权投影方法在揭示中药配伍规律与药物组合预测方面具有一定实用性和有效性。

基于改进OpenPose的人体关键点检测算法

人体关键点检测在人体姿态估计领域具有广泛应用场景,针对其检测速度慢、多人场景下无法实现关键点全局最优匹配的问题,论文提出了一种基于改进OpenPose的人体关键点检测算法。首先,对经典OpenPose前置特征提取网络所使用的普通3D卷积进行深度可分离卷积(DSC)替换,降低模型参数规模提高检测速度;然后,针对关键点坐标回归支路(PCM)对应的坐标标签值,提出了基于高斯核的标注策略,使得网络训练过程更加鲁棒;最后,基于匈牙利算法做二分图匹配,实现了多人场景下关键点的全局最优匹配。论文在COCO2017数据集上进行算法评估,在消融试验中,检测帧率FPS达到34,相对经典OpenPose提升了36%,对应AP^(50)、AP^(75)、AP^(90)指标分别达到92.5、81.4、70.8,提升了8.4%,9.1%,8.9%,且与其他关键点检测方案对比,具有较高的检测精度。

Comparisons and Contrasts between Asymmetry and Nestedness in Interacting Ecological Networks

We compare and contrast asymmetry and nestedness, two concepts used in the characterisation of the specialist-generalist balance in bipartite ecological interaction networks. Our analysis is relevant to mutualistic networks such as those consisting of flowering plants and pollinators, or fruiting plants and frugivores, or antagonistic networks such as those consisting of plants and herbivores, in an ecological community. We shall refer to the two sets of species in the bipartite network as plants and animals, the usual but not the only ecological situation. By asymmetry we mean either connectivity asymmetry or dependence asymmetry, which are essentially equivalent. Asymmetry expresses two attributes: generalists interact preferentially with specialists, and specialists avoid interacting with each other. Nested patterns, in principle, should express these same two features and one more: the presence of a core of interactions among generalists. We compute the full set of perfectly nested patterns that are possible in an L × L matrix with N interactions representing an ecological network of L plants and L animals, and point out that the number of nested arrangements grows exponentially with N. In addition, we analyse asymmetry for the full set of perfectly nested patterns, and identify extremes of asymmetry inside the universe of nested patterns. The minimal asymmetry is marked by a modular core of interactions between species that are neither specialists nor generalists. On the other hand, the case of maximal asymmetry is formed by a set of few generalists and many specialists with equal connectivity. The stereotypic case of nestedness with a core of interactions among generalists has intermediate asymmetry.

基于加权二部图及贪婪策略的蜂窝网络D2D通信资源分配

D2D(Device-to-Device)通信是解决频谱资源稀缺问题的关键技术之一。该文研究蜂窝网络中“many-tomany”的复杂场景,即单个RB(Resource Block)可以分配给多对D2D用户重用,并且允许单个D2D用户对使用多个RB,其中D2D用户对数量远多于蜂窝用户设备(Cellular User Equipment,CUE)数量和RB数量。考虑CUE对资源使用具有更高优先级,将此优化问题分解为蜂窝用户资源分配和D2D用户资源重用两个阶段。在第1阶段,提出基于公平性的循环二部图匹配(Fairness-based Circular Bipartite Graph Matching,FCBGM)算法,将现有的RB分配给所有CUE,以最大化蜂窝用户和速率。在第2阶段,分别提出基于二部图的资源重用(Bipartite Graph-based Resource Reuse,BGRR)算法和基于贪婪策略的资源重用(Greedy-based Resource Reuse,GRR)算法,目标是将已经分配给CUE的RB再次分配给D2D用户重用,以最大化系统和速率,同时确保CUE的基本速率需求。仿真结果表明,在D2D用户对数量远大于CUE数量和RB数量的情况下,与现有典型算法相比,所提算法能够有效提高系统和速率,增加D2D接入率,同时兼顾用户公平性和服务质量需求。

Personalized Recommendation Algorithm Based on Rating System and User Interest Association Network

In most available recommendation algorithms, especially for rating systems, almost all the high rating information is utilized on the recommender system without using any low-rating information, which may include more user information and lead to the accuracy of recommender system being reduced. The paper proposes a algorithm of personalized recommendation (UNP algorithm) for rating system to fully explore the similarity of interests among users in utilizing all the information of rating data. In UNP algorithm, the similarity information of users is used to construct a user interest association network, and a recommendation list is established for the target user with combining the user interest association network information and the idea of collaborative filtering. Finally, the UNP algorithm is compared with several typical recommendation algorithms (CF algorithm, NBI algorithm and GRM algorithm), and the experimental results on Movielens and Netflix datasets show that the UNP algorithm has higher recommendation accuracy.

A study of fault detection way for computer networks based on multiple stages

To relieve traliic overhead induced by active probing based methods, a new fault detection method, whose key is to divide the detection process into multiple stages, is proposed in this paper. During each stage, only a small region of the network is detected by using a small set of probes. Meanwhile, it also ensures that the entire network can be covered alter multiple detection stages. This method can guarantee that the traffic used by probes during each detection stage is small sufficiently so that the network can operate without severe disturbance from probes. Several simulation results verify the effectiveness of the proposed method.

一种基于图卷积神经网络的在线课程推荐系统

由于在线课程学习不受时间和地点限制,越来越受到广大求学者的青睐,但各大在线教育平台推出的在线课程数量较多,使得用户难以选择。课程推荐是解决“信息过载”的重要手段,然而现有的课程推荐模型对用户和课程隐式交互数据挖掘不足,为此,文中提出一种基于图卷积神经网络的在线课程推荐系统。首先利用用户和课程的多种交互行为分类构建用户-课程二部图;然后将课程知识信息融入用户-课程二部图,利用图卷积神经网络高阶连通性递归地在图上传播嵌入信息,深入挖掘“用户-课程-知识”的关联关系,并设计高效的在线课程推荐系统,迅速响应用户课程请求;最后选取三种经典的神经网络推荐模型进行对比分析。实验结果表明,所提方法具有较高的推荐准确率。