State estimation for complex systems with randomly occurring nonlinearities and randomly missing measurements

This paper is concerned with the state estimation problem for the complex networked systems with randomly occurring nonlinearities and randomly missing measurements. The nonlinearities are included to describe the phenomena of nonlinear disturbances which exist in the network and may occur in a probabilistic way. Considering the fact that probabilistic data missing may occur in the process of information transmission, we introduce the randomly data missing into the sensor measurements. The aim of this paper is to design a state estimator to estimate the true states of the considered complex network through the available output measurements. By using a Lyapunov functional and some stochastic analysis techniques, sufficient criteria are obtained in the form of linear matrix inequalities under which the estimation error dynamics is globally asymptotically stable in the mean square. Furthermore, the state estimator gain is also obtained. Finally, a numerical example is employed to illustrate the effectiveness of the proposed state estimation conditions.     

CAMAS: A cluster-aware multiagent system for attributed graph clustering

Attributed graphs describe nodes via attribute vectors and also relationships between different nodes via edges. To partition nodes into clusters with tighter correlations, an effective way is applying clustering techniques on attributed graphs based on various criteria such as node connectivity and/or attribute similarity. Even though clusters typically form around nodes with tight edges and similar attributes, existing methods have only focused on one of these two data modalities. In this paper, we comprehend each node as an autonomous agent and develop an accurate and scalable multiagent system for extracting overlapping clusters in attributed graphs. First, a kernel function with a tunable bandwidth factor δ is introduced to measure the influence of each agent, and those agents with highest local influence can be viewed as the “leader” agents. Then, a novel local expansion strategy is proposed, which can be applied by each leader agent to absorb the most relevant followers in the graph. Finally, we design the cluster-aware multiagent system (CAMAS), in which agents communicate with each other freely under an efficient communication mechanism. Using the proposed multiagent system, we are able to uncover the optimal overlapping cluster configuration, i.e. nodes within one cluster are not only connected closely with each other but also with similar attributes. Our method is highly efficient, and the computational time is shown that nearly linearly dependent on the number of edges when δ ∈ [0.5, 1). Finally, applications of the proposed method on a variety of synthetic benchmark graphs and real-life attributed graphs are demonstrated to verify the systematic performance.     

A Pseudo-document-based Topical N-grams model for short texts

World Wide Web - In recent years, short text topic modeling has drawn considerable attentions from interdisciplinary researchers. Various customized topic models have been proposed to tackle the...     

GLEAM: a graph clustering framework based on potential game optimization for large-scale social networks

With the growing explosion of online social networks, the study of large-scale graph clustering has attracted considerable interest. Most of traditional methods view the graph clustering problem as an optimization problem based on a given objective function; however, there are few methodical theories for the emergence of clusters over real-life networks. In this paper, each actor in online social networks is viewed as a selfish player in a non-cooperative game. The strategy associated with each node is defined as the cluster membership vector, and each one’s incentive is to maximize its own social identity by adopting the most suitable strategy. The definition of utility function in our game model is inspired by the conformity psychology, which is defined as the weighted average of one’s social identity by participating different clusters. With this setting, the proposed game can well match a potential game. So that the cluster could be shaped by the actions of those closely interactive users who adopt the same strategy in a Nash equilibrium. To this end, we propose a novel Graph cLustering framework based on potEntial gAme optiMization (GLEAM) for parallel graph clustering. It first utilize the cosine similarity to weight each edge in the original network. Then, an initial partition, including a number of clusters dominated by those potential “leader nodes”, is created by a fast heuristic process. Third, a potential game-based weighted Modularity optimization is used to improve the initial partition. Finally, we introduce the notion of potentially attractive cluster, and then discover the overlapping partition of the graph using a simple double-threshold procedure. Three phases in GLEAM are carefully designed for parallel execution. Experiments on real-world networks analyze the convergence inside GLEAM, and demonstrate the high performance of GLEAM by comparing it with the state-of-the-art community detection approaches in the literature.     

Efficient indexing for semantic search

The increasing performance and wider spread use of automated semantic annotation and entity linking platforms has empowered the possibility of using semantic information in information retrieval. While keyword-based information retrieval techniques have shown impressive performance, the addition of semantic information can increase retrieval performance by allowing for more accurate sense disambiguation, intent determination, and instance identification, just to name a few. Researchers have already delved into the possibility of integrating semantic information into practical search engines using a combination of techniques such as using graph databases, hybrid indices and adapted inverted indices, among others. One of the challenges with the efficient design of a search engine capable of considering semantic information is that it would need to be able to index information beyond the traditional information stored in inverted indices, including entity mentions and type relationships. The objective of our work in this paper is to investigate various ways in which different data structure types can be adopted to integrate three types of information including keywords, entities and types. We will systematically compare the performance of the different data structures for scenarios where (i) the same data structure types are adopted for the three types of information, and (ii) different data structure types are integrated for storing and retrieving the three different information types. We report our findings in terms of the performance of various query processing tasks such as Boolean and ranked intersection for the different indices and discuss which index type would be appropriate under different conditions for semantic search.     

Word-sentence co-ranking for automatic extractive text summarization

Extractive summarization aims to automatically produce a short summary of a document by concatenating several sentences taken exactly from the original material. Due to its simplicity and easy-to-use, the extractive summarization methods have become the dominant paradigm in the realm of text summarization. In this paper, we address the sentence scoring technique, a key step of the extractive summarization. Specifically, we propose a novel word-sentence co-ranking model named CoRank, which combines the word-sentence relationship with the graph-based unsupervised ranking model. CoRank is quite concise in the view of matrix operations, and its convergence can be theoretically guaranteed. Moreover, a redundancy elimination technique is presented as a supplement to CoRank, so that the quality of automatic summarization can be further enhanced. As a result, CoRank can serve as an important building-block of the intelligent summarization systems. Experimental results on two real-life datasets including nearly 600 documents demonstrate the effectiveness of the proposed methods.     

一种基于算法机制设计的社会法则合成方法

社会法则是在多Agent系统中为确立某种目标属性而对各个Agent实施的行为限制集合.在Agent具有“个体理性”及“私有信息”的“策略情况”下,社会法则合成问题不应建模成通常的优化问题,而应建模成算法机制设计问题.“最小化副作用”经常是社会法则需要满足的基本要求.从博弈论的角度来看,“最小化副作用”与“最大化社会福利”的概念紧密相关,可以将“最小化副作用的社会法则合成”建模为一种效率机制设计问题.不仅需要为给定目标属性找到有效且社会福利最大的社会法则,还需要向Agent支付适当的金额,以实现激励相容性和个体理性.首先基于VCG机制设计一种名叫VCG-SLM的效率机制,证明它可满足所有必需的形式属性.然而,由于发现可证明该机制的计算是一个FP^NP-完全问题,针对性地提出该机制的一种基于整数规划的实现方式VCG-SLM-ILP,基于ATL语义将分配及支付的计算转化为整数规划,并严格地证明其正确性,从而可有效利用目前已非常成熟的工业级整数规划求解器,成功解决棘手的机制计算问题.     

基于异质图表达学习的跨境电商推荐模型

跨境电商产品推荐已经成为电子商务领域新兴的研究议题之一。由于电商产品信息复杂多样、“用户-产品”关联矩阵极为稀疏并且冷启动问题突出,因此传统的协同过滤推荐模型很难奏效。而改进的深度协同过滤模型,只考虑了用户对产品的“显式”和“隐式”的反馈信息,忽视了由用户与项目组成的图结构信息,推荐性能很难满足平台和用户的要求。为了解决这些难题,该文提出基于异质图表达学习的图神经网络模型(HGNR)用于个性化的跨境电商产品推荐,该模型具有2个显著的优势:(1) 构造“用户-产品-主题”3部图作为模型的输入,通过图卷积神经网络(GCN)在异质图上进行高质量信息传播和聚合;(2)能够获取高质量的用户和产品表征向量,实现了用户和产品复杂交互关系的建模。在真实的跨境电商订单数据集上的实验结果表明,HGNR模型不仅在推荐性能上表现出色,还能有效提升冷启动用户的推荐准确率,与9种推荐基准算法相比,HGNR在评价指标HitRate@10, Item-coverage@10, MRR@10上至少提升了3.33%, 0.91%, 0.54%。     

Text summarization using unsupervised deep learning

We present methods of extractive query-oriented single-document summarization using a deep auto-encoder (AE) to compute a feature space from the term-frequency (tf) input. Our experiments explore both local and global vocabularies. We investigate the effect of adding small random noise to local tf as the input representation of AE, and propose an ensemble of such noisy AEs which we call the Ensemble Noisy Auto-Encoder (ENAE). ENAE is a stochastic version of an AE that adds noise to the input text and selects the top sentences from an ensemble of noisy runs. In each individual experiment of the ensemble, a different randomly generated noise is added to the input representation. This architecture changes the application of the AE from a deterministic feed-forward network to a stochastic runtime model. Experiments show that the AE using local vocabularies clearly provide a more discriminative feature space and improves the recall on average 11.2%. The ENAE can make further improvements, particularly in selecting informative sentences. To cover a wide range of topics and structures, we perform experiments on two different publicly available email corpora that are specifically designed for text summarization. We used ROUGE as a fully automatic metric in text summarization and we presented the average ROUGE-2 recall for all experiments.