Learning short synfire chains by self-organization

A model of cortical neurons capable of sustaining a low level of spontaneous activity is investigated. Without learning the activity of the network is chaotic. We report on attempts to learn synfire chains in this type of network by introducing a Hebbian learning mechanism and exciting a small set of neurons at random intervals. We discuss the types of instabilities that can arise and prevent the formation of long synfire chains and also discuss various biologically plausible mechanisms which to some extent cure these instabilities.     

STDP provides the substrate for igniting synfire chains by spatiotemporal input patterns

Spike-timing-dependent synaptic plasticity (STDP), which depends on the temporal difference between pre- and postsynaptic action potentials, is observed in the cortices and hippocampus. Although several theoretical and experimental studies have revealed its fundamental aspects, its functional role remains unclear. To examine how an input spatiotemporal spike pattern is altered by STDP, we observed the output spike patterns of a spiking neural network model with an asymmetrical STDP rule when the input spatiotemporal pattern is repeatedly applied. The spiking neural network comprises excitatory and inhibitory neurons that exhibit local interactions. Numerical experiments show that the spiking neural network generates a single global synchrony whose relative timing depends on the input spatiotemporal pattern and the neural network structure. This result implies that the spiking neural network learns the transformation from spatiotemporal to temporal information. In the literature, the origin of the synfire chain has not been sufficiently focused on. Our results indicate that spiking neural networks with STDP can ignite synfire chains in the cortices.     

有线网络中虚拟网络映射算法研究

网络虚拟化是未来网络的关键技术之一,有助于克服当前网络的“僵化”问题,能够在无需对当前网络架构做出巨大改变的基础上配置新的网络协议和服务,实现多个虚拟网络共存于一个物理网络上,由此产生了新的问题,如何将有限的物理资源合理分配给不同的虚拟网络,即虚拟网络映射问题。根据网络环境,可以分为有线网络和无线网络下的虚拟网络映射。其中,有线网络下的映射是研究虚拟网络映射问题的基础和重点,已有大量算法提出。为了给该问题的研究提供一个全面的视野,从问题定义、存在挑战、映射目标方面对有线网络中虚拟网络映射算法进行综述,根据算法的不同特点进行分类,重点介绍几种典型的算法并进行比较总结,最后指出未来的研究趋势。     

基于AWGR的动态光网络及拓扑映射

随着数据中心规模的越来越大,同一个虚拟拓扑中虚拟节点所映射到的物理节点间的距离越来越远,其链路在映射过程中需要经过若干的跳步,占用了大量的物理网络资源,降低了数据中心的收益.受到数据中心固定拓扑的限制,仅通过映射算法的优化很难取得较好的性能和收益提升,因此提出一种基于AWGR的动态光网络和对应的虚拟拓扑映射方法,通过结...     

Adversarial network embedding using structural similarity

Network embedding which aims to embed a given network into a low-dimensional vector space has been proved effective in various network analysis and mining tasks such as node classification,link prediction and network visualization.The emerging network embedding methods have shifted of emphasis in utilizing mature deep learning models.The neural-network based network embedding has become a mainstream solution because of its high eficiency and capability of preserv-ing the nonlinear characteristics of the network.In this paper,we propose Adversarial Network Embedding using Structural Similarity(ANESS),a novel,versatile,low-complexity GAN-based network embedding model which utilizes the inherent vertex-to-vertex structural similarity attribute of the network.ANESS learns robustness and ffective vertex embeddings via a adversarial training procedure.Specifically,our method aims to exploit the strengths of generative adversarial networks in generating high-quality samples and utilize the structural similarity identity of vertexes to learn the latent representations of a network.Meanwhile,ANESS can dynamically update the strategy of generating samples during each training iteration.The extensive experiments have been conducted on the several benchmark network datasets,and empirical results demon-strate that ANESS significantly outperforms other state-of-theart network embedding methods.     

面向动态虚拟网络请求的虚拟网络映射算法

针对虚拟网络请求资源动态变化的实际情况,提出了面向动态虚拟网络请求的虚拟网络映射（DVNR-VNE）算法。以混合线性规划理论为基础,采用多队列的方式分别对不同类型的虚拟网络请求进行预处理,建立了以最小化映射代价和最小迁移代价为优化目标的映射模型,优先映射需要释放资源的请求以获得更多的资源支持其他的虚拟网络,对新到来的虚拟网络请求采用优化后的虚拟网络映射（WD-VNE）算法进行映射。仿真实验表明,该算法降低了链路映射成本和迁移成本并获得了较高的虚拟网络请求接受率。     

OFNE: a framework of opinion features regulated network embedding

The Journal of Supercomputing - Network embedding technologies that transform the nodes of a network into a low-dimensional vector space have many various potential applications such as node...     

Designing balanced wrapper chains in 3D SoC under constrained TSVs

Innovations in Systems and Software Engineering - Three-dimensional integrated circuit (3D-IC) has emerged as a savior of failing Moore’s law, where reduced length of interconnects is...     

Learning knowledge graph embedding with a bi-directional relation encoding network and a convolutional autoencoder decoding network

Neural Computing and Applications - Derived from knowledge bases, knowledge graphs represent knowledge expressions in graphs, which utilize nodes and edges to denote entities and relations...     

基于网络中心性分析的虚拟网络映射算法

定义了有权网络节点紧密度和路径中心度,并提出了基于网络中心性分析的虚拟网络映射算法。该算法是一个两阶段映射算法,从全局角度分别对底层节点和映射路径进行了有效的定量评估,提高了映射资源选择的均衡性。仿真实验结果表明,与现有的主流研究成果相比,该算法显著地提高了虚拟网络请求接受率。     

基于混合群智能优化的虚拟网络映射算法

网络虚拟化是突破网络发展僵局的一项重要技术,而虚拟网络映射(VNE)是网络虚拟化的一个主要问题。提高底层网络资源的利用率和收益是虚拟网络映射的主要目标。针对底层网络支持路径分裂的情况,建立了整数线性规划(ILP)模型,并提出基于混合群智能优化的虚拟网络映射算法。该算法在兼顾映射开销和映射均衡性的基础上利用粒子群优化算法(PSO)和遗传算法(GA)迭代优化映射方案。仿真实验结果表明,与现有的主流研究成果相比,该算法显著地提高了底层网络长期平均运营收益与虚拟网络请求接受率。     

Heterogeneous-attributes enhancement deep framework for network embedding

Network embedding, which targets at learning the vector representation of vertices, has become a crucial issue in network analysis. However, considering the complex structures and heterogeneous attributes in real-world networks, existing methods may fail to handle the inconsistencies between the structure topology and attribute proximity. Thus, more comprehensive techniques are urgently required to capture the highly non-linear network structure and solve the existing inconsistencies with retaining more information. To that end, in this paper, we propose a heterogeneous-attributes enhancement deep framework (HEDF), which could better capture the non-linear structure and associated information in a deep learningway, and effectively combine the structure information of multi-views by the combining layer. Along this line, the inconsistencies will be handled to some extent and more structure information will be preserved through a semi-supervised mode. The extensive validations on several real-world datasets show that our model could outperform the baselines, especially for the sparse and inconsistent situation with less training data.     

基于递归投影的结构性网络嵌入

近些年来,在网络嵌入（network embedding）领域的大多数研究都着眼于基于网络节点邻接关系的社区身份,如node2vec和DeepWalk;而基于网络拓扑结构的结构身份研究则十分匮乏,前沿方法如struc2vec等,通常效率很低。提出了递归结构性网络嵌入（recurrent structural network embedding,RSNE）,一种新颖而高效的结构特征学习方法。RSNE递归式地把节点的结构身份定义为其邻居结构身份的非线性投影。为了避免退化为基于邻接关系的聚类,采用了一种有效而鲁棒的初始化方法。理论分析显示RSNE在时间复杂度上显著优于现有的结构性网络嵌入方法,可视化与量化实验结果也表明RSNE在分类准确性和鲁棒性上达到了最新方法相同或更好的效果,同时消耗的计算时间与空间消耗也远远更少。     

融合属性信息的异质网络嵌入方法

现有的异质网络嵌入方法不仅忽略了网络中的异质边及其对节点嵌入的不同影响,还未考虑到网络结构与节点属性的融合。为此提出了一种融合属性信息的异质网络嵌入方法（SHANE）。将序列到序列（seq2seq）模型应用到依据边类型划分的子图中,无缝融合节点的结构信息和属性信息,同时捕捉节点的高阶语义信息。实验表明,SHANE在两个不同类型的数据集中进行链接预测任务,可以取得相对显著的效果。     

Sampling informative context nodes for network embedding

Several modern network embedding methods learn vector representations from sampled context nodes.The sampling strategies are often carefully designed and contro...     

基于中心度寻核的能效优化虚拟网映射算法

虚拟网映射是网络虚拟化技术的关键问题,以往研究常关注供应商的收益与开销,而网络设备的大量能源浪费使得供应商开始关注节能.将紧密中心度概念引入虚拟网映射问题中,同时考虑节点的位置和能力,优先使用已工作节点和缩短链路长度来降低能耗,提出了一种寻找核心节点优先映射(寻核)算法.该算法通过检验确保所选底层核心节点满足虚拟核心节点要求,节点和链路映射同步进行,同时根据贪婪策略保证所选底层网络节点跳数较小.仿真实验结果表明,该算法能够提高映射接收率约10％、改善收益开销比和收益能耗比10％以上.     

基于软件定义网络的可靠性虚拟网络映射保障机制

在软件定义网络（SDN）虚拟网络映射中,现有研究者主要考虑请求接受率方面,而忽视了SDN中底层资源失效的问题。为此,针对SDN中可靠性虚拟网络映射（SVNE）问题,提出了一种联合先验式保护和后验式恢复的虚拟网络映射保障机制。首先,在虚拟请求接受之前,对SDN物理网络区域性资源进行感知;然后,采用先验式保护机制为映射域内相对剩余资源变小的虚拟网络元素预留备份物理资源,并将此扩展虚拟网络通过D-ViNE算法映射至物理网络中;最后,在未备份虚拟网络元素发生故障时,采用后验式恢复算法完成故障的恢复,对节点和链路分别采用重映射和重路由的方法完成恢复。实验结果表明,与基于SDN的生存性虚拟网络映射算法（SDN-SVNE）相比,在虚拟请求接受率方面提高了21.9%。另外,该保护机制在虚拟级别故障恢复率、物理级别故障恢复率等方面也具有优势。     

On generalized balanced realizations

The class of analytic time-varying linear systems is considered. Different balanced realizations of such systems are defined, and their existence and properties are analyzed. The results are then used to derive reduced order approximations (also for unstable systems). A method is suggested to determine the order of a "good" approximation.     

基于异质用户网络嵌入的服务推荐方法研究

服务推荐过程中,为充分利用用户标签标注关系与用户的社交关系信息,提升推荐结果的准确性,提出一种基于异质用户网络嵌入的方法,通过将用户节点映射为一个低维的向量,再利用得到的用户向量进行协同推荐。在公开数据集Delicious上进行了实证分析,实验结果表明,相对已有的2个方法,该方法的推荐精度可分别提高18.1%和16.6%,且发现在学习用户表征向量时,节点之间的直接关系与"朋友的朋友"关系对表示用户节点结构信息同等重要;同时,推荐过程中为目标用户返回的相似用户在25个最为适宜。