基于深度神经网络和门控循环单元的动态图表示学习方法

学习图中节点的潜在向量表示是一项重要且普遍存在的任务,旨在捕捉图中节点的各种属性。大量工作证明静态图表示已经能够学习到节点的部分信息,然而,真实世界的图是随着时间的推移而演变的。为了解决多数动态网络算法不能有效保留节点邻域结构和时态信息的问题,提出了基于深度神经网络（DNN）和门控循环单元（GRU）的动态网络表示学习方法DynAEGRU。该方法以自编码器作为框架,其中的编码器首先用DNN聚集邻域信息以得到低维特征向量,然后使用GRU网络提取节点时态信息,最后用解码器重构邻接矩阵并将其与真实图对比来构建损失。通过与几种静态图和动态图表示学习算法在3个数据集上进行实验分析,结果表明DynAEGRU具有较好的性能增益。     

A high performance optimal dynamic routing algorithm with unicast multichannel QoS guarantee in communication systems

Dynamic routing protocols play an important role in today??s networks. In communication networks, in a current data transmission session, failing nodes and links is a destructor event which loses packets immediately and it can also waste network resources and services seriously. Sometimes failing nodes can disconnect data transmission and, therefore, lost packets must be retransmitted by new session. In this situation, the routing algorithm must discard failed nodes and must repair paths of session by rerouting them. In this case, static routing algorithms and some existing dynamic routing algorithms cannot manage faulty paths fairly and network efficiency is seriously declined. The capability to compensate for topology changes is the most important advantage dynamic routing offers over static routing. An efficient dynamic routing algorithm tries to reroute and change faulty paths without disconnecting sessions and keeps packet transmission in a desirable rate. It is important to tell that a dynamic routing algorithm should provide multi essential parameters, such as acceptable delay, jitter, bandwidth, multichannel paths, virtual channel connections, label switching technology, optimal resource allocation, optimal efficiency in the case of multimedia, and real time applications. This paper proposes a new dynamic framework which transforms static routing algorithms to dynamic routing algorithms. Using the new dynamic framework, this paper constructs an Optimal Dynamic Unicast Multichannel QoS Routing (ODUMR) algorithm based on the Constrained Based Routing (CBR) and Label Switching Technology which is called as ODUMR Algorithm. The performance of ODUMR is analyzed by network simulator tools such as OpNet, MATLAB, and WinQSB. ODUMR produces results better than the existing static and dynamic routing algorithms in terms of necessary parameters.     

Incremental K-clique clustering in dynamic social networks

Clustering entities into dense parts is an important issue in social network analysis. Real social networks usually evolve over time and it remains a problem to efficiently cluster dynamic social networks. In this paper, a dynamic social network is modeled as an initial graph with an infinite change stream, called change stream model, which naturally eliminates the parameter setting problem of snapshot graph model. Based on the change stream model, the incremental version of a well known k-clique clustering problem is studied and incremental k-clique clustering algorithms are proposed based on local DFS (depth first search) forest updating technique. It is theoretically proved that the proposed algorithms outperform corresponding static ones and incremental spectral clustering algorithm in terms of time complexity. The practical performances of our algorithms are extensively evaluated and compared with the baseline algorithms on ENRON and DBLP datasets. Experimental results show that incremental k-clique clustering algorithms are much more efficient than corresponding static ones, and have no accumulating errors that incremental spectral clustering algorithm has and can capture the evolving details of the clusters that snapshot graph model based algorithms miss.     

Online dynamic graph drawing

This paper presents an algorithm for drawing a sequence of graphs online. The algorithm strives to maintain the global structure of the graph and thus the user's mental map, while allowing arbitrary modifications between consecutive layouts. The algorithm works online and uses various execution culling methods in order to reduce the layout time and handle large dynamic graphs. Techniques for representing graphs on the GPU allow a speedup by a factor of up to 17 compared to the CPU implementation. The scalability of the algorithm across GPU generations is demonstrated. Applications of the algorithm to the visualization of discussion threads in Internet sites and to the visualization of social networks are provided.     

Inverse Markov Process Based Constrained Dynamic Graph Layout

In online dynamic graph drawing,constraints over nodes and node pairs help preserve a coherent mental map in a sequence of graphs.Defining the constraints is challenging due to the requirements of both preserving mental map and satisfying the visual aesthetics of a graph layout.Most existing algorithms basically depend on local changes but fail to do proper evaluations on the global propagation when setting constraints.To solve this problem,we introduce a heuristic model derived from PageRank which simulates the node movement as an inverse Markov process hence to give a global analysis of the layout's change,according to which different constraints can be set.These constraints,along with stress function,generate layouts maintaining spatial positions and shapes of relatively stable substructures between adjacent graphs.Experiments demonstrate that our method preserves both structure and position similarity to help users track graph changes visually.     

Techniques for Edge Stratification of Complex Graph Drawings

We propose an approach that allows a user (e.g., an analyst) to explore a layout produced by any graph drawing algorithm, in order to reduce the visual complexity and clarify its presentation. Our approach is based on stratifying the drawing into layers with desired properties; to this aim, heuristics are presented. The produced layers can be explored and combined by the user to gradually acquire details. We present a user study to test the effectiveness of our approach. Furthermore, we performed an experimental analysis on popular force-directed graph drawing algorithms, in order to evaluate what is the algorithm that produces the smallest number of layers and if there is any correlation between the number of crossings and the number of layers of a graph layout. The proposed approach is useful to explore graph layouts, as confirmed by the presented user study. Furthermore, interesting considerations arise from the experimental evaluation, in particular, our results suggest that the number of layers of a graph layout may represent a reliable measure of its visual complexity. The algorithms presented in this paper can be effectively applied to graph layouts with a few hundreds of edges and vertices. For larger drawings that contain lots of crossings, the time complexity of our algorithms grows quadratically in the number of edges and more efficient techniques need to be devised. The proposed approach takes as input a layout produced by any graph drawing algorithm, therefore it can be applied in a variety of application domains. Several research directions can be explored to extend our framework and to devise new visualization paradigms to effectively present stratified drawings.     

SetCoLa: High‐Level Constraints for Graph Layout

Constraints enable flexible graph layout by combining the ease of automatic layout with customizations for a particular domain. However, constraint‐based layout often requires many individual constraints defined over specific nodes and node pairs. In addition to the effort of writing and maintaining a large number of similar constraints, such constraints are specific to the particular graph and thus cannot generalize to other graphs in the same domain. To facilitate the specification of customized and generalizable constraint layouts, we contribute SetCoLa: a domain‐specific language for specifying high‐level constraints relative to properties of the backing data. Users identify node sets based on data or graph properties and apply high‐level constraints within each set. Applying constraints to node sets rather than individual nodes reduces specification effort and facilitates reapplication of customized layouts across distinct graphs. We demonstrate the conciseness, generalizability, and expressiveness of SetCoLa on a series of real‐world examples from ecological networks, biological systems, and social networks.     

Coherent time-varying graph drawing with multifocus+context interaction

We present a new approach for time-varying graph drawing that achieves both spatiotemporal coherence and multifocus+context visualization in a single framework. Our approach utilizes existing graph layout algorithms to produce the initial graph layout, and formulates the problem of generating coherent time-varying graph visualization with the focus+context capability as a specially tailored deformation optimization problem. We adopt the concept of the super graph to maintain spatiotemporal coherence and further balance the needs for aesthetic quality and dynamic stability when interacting with time-varying graphs through focus+context visualization. Our method is particularly useful for multifocus+context visualization of time-varying graphs where we can preserve the mental map by preventing nodes in the focus from undergoing abrupt changes in size and location in the time sequence. Experiments demonstrate that our method strikes a good balance between maintaining spatiotemporal coherence and accentuating visual foci, thus providing a more engaging viewing experience for the users.     

Intrinsically dynamic network communities

Community finding algorithms for networks have recently been extended to dynamic data. Most of these recent methods aim at exhibiting community partitions from successive graph snapshots and thereafter connecting or smoothing these partitions using clever time-dependent features and sampling techniques. These approaches are nonetheless achieving longitudinal rather than dynamic community detection. We assume that communities are fundamentally defined by the repetition of interactions among a set of nodes over time. According to this definition, analyzing the data by considering successive snapshots induces a significant loss of information: we suggest that it blurs essentially dynamic phenomena—such as communities based on repeated inter-temporal interactions, nodes switching from a community to another across time, or the possibility that a community survives while its members are being integrally replaced over a longer time period. We propose a formalism which aims at tackling this issue in the context of time-directed datasets (such as citation networks), and present several illustrations of both empirical and synthetic dynamic networks. We eventually introduce intrinsically dynamic metrics to qualify temporal community structure and emphasize their possible role as an estimator of the quality of the community detection—taking into account the fact that various empirical contexts may call for distinct ‘community’ definitions and detection criteria.     

Seed Selection for Spread of Influence in Social Networks: Temporal vs. Static Approach

The problem of finding optimal set of users for influencing others in the social network has been widely studied. Because it is NP-hard, some heuristics were proposed to find sub-optimal solutions. Still, one of the commonly used assumption is the one that seeds are chosen on the static network, not the dynamic one. This static approach is in fact far from the real-world networks, where new nodes may appear and old ones dynamically disappear in course of time. The main purpose of this paper is to analyse how the results of one of the typical models for spread of influence - linear threshold - differ depending on the strategy of building the social network used later for choosing seeds. To show the impact of network creation strategy on the final number of influenced nodes - outcome of spread of influence, the results for three approaches were studied: one static and two temporal with different granularities, i.e. various number of time windows. Social networks for each time window encapsulated dynamic changes in the network structure. Calculation of various node structural measures like degree or betweenness respected these changes by means of forgetting mechanism - more recent data had greater influence on node measure values. These measures were, in turn, used for node ranking and their selection for seeding. All concepts were applied to experimental verification on five real datasets. The results revealed that temporal approach is always better than static and the higher granularity in the temporal social network while seeding, the more finally influenced nodes. Additionally, outdegree measure with exponential forgetting typically outperformed other time-dependent structural measures, if used for seed candidate ranking.     

Customizing a Fisheye View Algorithm to Preserve the Mental Map

Frequently, large knowledge bases are represented by graphs. Many visualization tools allow users or other applications to interact with and adjust the layouts of these graphs. One layout adjustment problem is that of showing more detail without eliding parts of the graph. Approaches based on a fisheye lens paradigm seem well suited to this task. However, many of these techniques are non-trivial to implement and their distortion techniques often cannot be altered to suit different graph layouts. When distorting a graph layout, it is often desirable to preserve various properties of the original graph in an adjusted view. Pertinent properties may include straightness of lines, graph topology, orthogonalities and proximities. However, it is normally not possible to preserve all of the original properties of the graph layout. The type of layout and its application should be considered when deciding which properties to preserve or distort. This paper describes a fisheye view algorithm which can be customized to suit various different graph layouts. In contrast to other methods, the user can select which properties of the original graph layout to preserve in an adjusted view. The technique is demonstrated through its application to visualizing structures in large software systems.     

基于多通道时空编码器的交通流量预测模型

传统的交通流量预测模型对历史数据进行时空建模,忽略了交通数据的时间周期性内部潜在关系和交通路网间节点的距离特征和相似性空间特征。据此,提出面向交通流量预测的多通道时空编码器模型MC-STGNN,用来提高交通流量预测的准确率。首先将交通数据处理成三通道的周期性时间序列,并对整体的序列数据进行时间位置编码和自适应的空间位置编码,提取路网节点间的动态相关性;其次引入具有卷积结构的多头自我注意力机制,更大程度地捕获周期数据不同程度的时间相关性;最后提出一种图生成器生成新的时空图,提取路网节点间的相似性和距离特征,并利用门控图卷积网络整合原始图和新时空图的空间信息。在高速公路数据集PEMS03和PEMS08上进行一小时的交通流量综合预测实验,结果表明,MC-STGNN模型与其他的基线模型相比,具有更佳的性能指标,说明MC-STGNN模型具有更优的建模能力。     

Heuristic Methods for Minimum-Cost Pipeline Network Design – a Node Valency Transfer Metaheuristic

Designing low-cost network layouts is an essential step in planning linked infrastructure. For the case of capacitated trees, such as oil or gas pipeline networks, the cost is usually a function of both pipeline diameter (i.e. ability to carry flow or transferred capacity) and pipeline length. Even for the case of incompressible, steady flow, minimizing cost becomes particularly difficult as network topology itself dictates local flow material balances, rendering the optimization space non-linear. The combinatorial nature of potential trees requires the use of graph optimization heuristics to achieve good solutions in reasonable time. In this work we perform a comparison of known literature network optimization heuristics and metaheuristics for finding minimum-cost capacitated trees without Steiner nodes, and propose novel algorithms, including a metaheuristic based on transferring edges of high valency nodes. Our metaheuristic achieves performance above similar algorithms studied, especially for larger graphs, usually producing a significantly higher proportion of optimal solutions, while remaining in line with time-complexity of algorithms found in the literature. Data points for graph node positions and capacities are first randomly generated, and secondly obtained from the German emissions trading CO₂ source registry. As political will for applications and storage for hard-to-abate industry CO₂ emissions is growing, efficient network design methods become relevant for new large-scale CO₂ pipeline networks.

     

基于时序模体注意力图卷积的动态网络链路预测算法

时序网络中的动态链路预测旨在基于历史连边信息预测未来会产生的连边,是网络分析的重要组成部分,具有极大的理论研究价值和广阔的应用场景.针对现有的动态链路预测算法大多基于一阶连边关系预测未来连边,忽略了对高阶的拓扑信息和时序通联信息的挖掘和利用问题,提出一种基于时序模体注意力图卷积的动态链路预测算法.首先,提出一种时序模体邻接矩阵构建算法,利用时序模体抽取节点间的高阶拓扑和时序关系信息;然后利用隐式调节过程对网络演化过程进行建模,并使用时序模体邻接矩阵作为传输矩阵的图卷积神经网络学习节点的低维向量表示并进行迭代更新;最后以节点间表示向量作为输入,通过计算连边发生的条件密度函数值作为依据完成动态链路预测.在多个真实时序网络数据集上的实验结果表明,所提算法可有效挖掘节点间的高阶拓扑和时序信息,提高动态链路预测效果.     

多视角融合的时空动态图卷积网络城市交通流量预测

城市交通流量预测是构建绿色低碳、安全高效的智能交通系统的重要组成部分.时空图神经网络由于具有强大的时空数据表征能力,被广泛应用于城市交通流量预测.当前时空图神经网络在城市交通流量预测中仍存在以下两方面局限性:1)直接构建静态路网拓扑图对城市空间相关性进行表示,忽略了节点的动态交通模式,难以表达节点流量之间的时序相似性,无法捕获路网节点之间在时序上的动态关联.2)只考虑路网节点的局部空间相关性,忽略节点的全局空间相关性,无法建模交通路网中局部区域和全局空间之间的依赖关系.为打破上述局限性,本文提出了一种多视角融合的时空动态图卷积模型用于预测交通流量.首先,从静态空间拓扑和动态流量模式视角出发,构建路网空间结构图和动态流量关联图,并使用动态图卷积学习节点在两种视角下的特征,全面捕获城市路网中多元的空间相关性.其次,从局部视角和全局视角出发,计算路网的全局表示,将全局特征与局部特征融合,增强路网节点特征的表现力,发掘城市交通流量的整体结构特征.接下来,设计了局部卷积多头自注意力机制来获取交通数据的动态时间相关性,实现在多种时间窗口下的准确流量预测.最后,在四种真实交通数据上的实验结果证明了本文模型的有效性和准确性.     

Finding overlapping communities in a complex network of social linkages and Internet of things

Online social networks play an important role in today’s Internet. These social networks contain huge amounts of data and the integrated framework of SN with Internet of things (IoT) presents a challenging problem. IoT is the ubiquitous interconnection of everyday items of interest (things), providing connectivity anytime, anywhere, and with anything. Like biological, co-authorship, and virus-spread networks, IoT and Social Network (SN) can be characterized to be complex networks containing substantial useful information. In the past few years, community detection in graphs has been an active area of research (Lee and Won in Proceedings of IEEE SoutheastCon, pp. 1–5, 2012). Many graph mining algorithms have been proposed, but none of them can help in capturing an important dimension of SNs, which is friendship. A friend circle expands with the help of mutual friends, and, thus, mutual friends play an important role in social networks’ growth. We propose two graph clustering algorithms: one for undirected graphs such as Facebook and Google+, and the other for directed graphs such as Twitter. The algorithms extract communities, and based on the access control policy nodes share resources (things). In the proposed Community Detection in Integrated IoT and SN (CDIISN) algorithm, we divide the nodes/actors of complex networks into basic, and IoT nodes. We, then, execute the community detection algorithm on them. We take nodes of a graph as members of a SN, and edges depicting the relations between the nodes. The CDIISN algorithm is purely deterministic, and no fuzzy communities are formed. It is known that one community detection algorithm is not suitable for all types of networks. For different network structures, different algorithms exhibit different results, and methods of execution. However, in our proposed method, the community detection algorithm can be modified as desired by a user based on the network connections. The proposed community detection approach is unique in the sense that a user can define his community detection criteria based on the kind of network.     

基于社区的动态网络节点介数中心度更新算法

随着互联网技术的迅猛发展,社会网络呈现出爆炸增长的趋势,传统的静态网络分析方法越来越难以达到令人满意的效果,于是对网络进行动态分析就成为社会网数据管理领域的一个研究热点。节点介数中心度衡量的是一个节点对图中其他点对最短路径的控制能力,有利于挖掘社会网络中的重要节点。在图结构频繁变化的场合,若每次变化后都重新计算整个图中所有节点的介数中心度,则效率将会很低。针对动态网络中节点介数中心度计算困难的问题,本文提出一种基于社区的节点介数中心度更新算法。通过维护社区与社区、社区与节点的最短距离集合,快速过滤掉那些在网络动态更新中不受影响的点对,从而大大提高节点介数中心度的更新效率。真实数据集和合成数据集上的实验结果表明了论文所提算法的有效性。     

Temporal link prediction in multi-relational network

Link prediction problem in complex networks has received substantial amount of attention in the field of social network analysis. Though initial studies consider only static snapshot of a network, importance of temporal dimension has been observed and cultivated subsequently. In recent times, multi-domain relationships between node-pairs embedded in real networks have been exploited to boost link prediction performance. In this paper, we combine multi-domain topological features as well as temporal dimension, and propose a robust and efficient feature set called TMLP (Time-aware Multi-relational Link Prediction) for link prediction in dynamic heterogeneous networks. It combines dynamics of graph topology and history of interactions at dyadic level, and exploits time-series model in the feature extraction process. Several experiments on two networks prepared from DBLP bibliographic dataset show that the proposed framework outperforms the existing methods significantly, in predicting future links. It also demonstrates the necessity of combining heterogeneous information with temporal dynamics of graph topology and dyadic history in order to predict future links. Empirical results find that the proposed feature set is robust against longitudinal bias.