Potential Theory for Directed Networks

Zhang, Qian-Ming; Lü, Linyuan; Wang, Wen-Qiang; Zhou, Tao
February 2013
PLoS ONE;Feb2013, Vol. 8 Issue 2, p1
Academic Journal
Uncovering factors underlying the network formation is a long-standing challenge for data mining and network analysis. In particular, the microscopic organizing principles of directed networks are less understood than those of undirected networks. This article proposes a hypothesis named potential theory, which assumes that every directed link corresponds to a decrease of a unit potential and subgraphs with definable potential values for all nodes are preferred. Combining the potential theory with the clustering and homophily mechanisms, it is deduced that the Bi-fan structure consisting of 4 nodes and 4 directed links is the most favored local structure in directed networks. Our hypothesis receives strongly positive supports from extensive experiments on 15 directed networks drawn from disparate fields, as indicated by the most accurate and robust performance of Bi-fan predictor within the link prediction framework. In summary, our main contribution is twofold: (i) We propose a new mechanism for the local organization of directed networks; (ii) We design the corresponding link prediction algorithm, which can not only testify our hypothesis, but also find out direct applications in missing link prediction and friendship recommendation.


Related Articles

  • Descubrimiento de conocimiento en lecciones aprendidas documentadas en los procesos de cierre de proyectos informáticos. Bárbara Ril Valentin, Eliana; Rodríguez Puente, Rafael; Piñero Pérez, Pedro Y.; Martínez Noriegas, Hugo A. // Revista Cubana de Ciencias Informáticas;jul-sep2013, Vol. 7 Issue 3, p45 

    The documentation of learned lessons allows us to see past mistakes and improve future work. Learning from experience of previous projects help us to reduce risks, to avoid problems already identified and to reuse best practices to reduce the number of unsuccessful projects. The goal of this...

  • COMPACT KNOWLEDGE DISCOVERY IN DATABASES: A CORE BASED APPROACH. Bhatkar, Anup // Computer Science & Telecommunications;2012, Vol. 33 Issue 1, p3 

    The purpose of Data Mining is to facilitate understanding large amounts of data by discovering interesting regularities or exceptions. Association rules are simple but powerful regularities in binary data. However, there can be easily hundreds or even more association rules holding in a data set...

  • APPLICATION OF CLUSTERING TO ANALYZE ACADEMIC SOCIAL NETWORKS. Rani, K. Sobha; Raju, K. V. S. V. N.; Kumari, V. Valli // International Journal of Web & Semantic Technology;Apr2013, Vol. 4 Issue 2, p9 

    Social network is a group of individuals with diverse social interactions amongst them. The network is of large scale and distributed due to involvement of more people from different parts of the globe. Quantitative analysis of networks is need of the hour due to its' rippling influence on the...

  • CONCEPTUAL KNOWLEDGE PROCESSING GROUNDED LOGICAL INFORMATION SYSTEM FOR ONCOLOGICAL DATABASES - EXTENDED ABSTRACT. Brad, A.; Neamţiu, L.; Răusanu, S.; Săcărea, C. // Studia Universitatis Babes-Bolyai, Informatica;2011, Vol. 56 Issue 2, p51 

    Conceptual Knowledge Processing is a fundamental paradigm in data analysis and knowledge management. We use several methods of Conceptual Knowledge Processing to build a Logical Information System (LIS) for Oncological Databases. This paper describes this approach by analyzing the use of these...

  • Performance Scalability of Data-Mining Workloads in Bioinformatics. Yurong Chen; Qian Diao; Carole Dulong; Chunrong Lai; Wei Hu; Eric Li; Wenlong Li; Tao Wang; Yimin Zhang // Intel Technology Journal;May2005, Vol. 9 Issue 2, p131 

    Data mining is the extraction of hidden predictive information from large data bases. Emerging data-mining applications are important factors to drive the architecture of future microprocessors. This paper analyzes the performance scalability on parallel architectures of such applications to...

  • Exploiting Publication Contents and Collaboration Networks for Collaborator Recommendation. Kong, Xiangjie; Jiang, Huizhen; Yang, Zhuo; Xu, Zhenzhen; Xia, Feng; Tolba, Amr // PLoS ONE;2/5/2016, Vol. 11 Issue 2, p1 

    Thanks to the proliferation of online social networks, it has become conventional for researchers to communicate and collaborate with each other. Meanwhile, one critical challenge arises, that is, how to find the most relevant and potential collaborators for each researcher? In this work, we...

  • Tripos embraces service-oriented informatics.  // Scientific Computing World;Jul/Aug2005, Issue 83, p8 

    This article reports on the plan of Tripos, a company that provides drug discovery chemistry and informatics products, to include Web services within its Discovery Informatics software and product development strategy. The company's support of Service-Oriented Informatics will ultimately provide...

  • HOW ORGANIZATIONAL NETWORK ANALYSIS FACILITATED TRANSITION FROM REGIONAL TO A GLOBAL IT FUNCTION. Cross, Rob; Dowling, Christie; Gerbasi, Alexandra; Gulas, Vic; Thomas, Robert J. // MIS Quarterly Executive;2010, Vol. 9 Issue 3, p133 

    IT executives in most large enterprises must build organizations that can adapt and thrive in a global economy while operating with fewer resources. Yet despite implementing sophisticated organizational redesigns and collaboration technologies, improvements in performance are frequently...

  • SEMANTIC CLASSIFICATION OF TEXT MESSAGES USING THE CONCEPT OF COMMUNITY IN SOCIAL NETWORK ANALYSIS. Hideya Matsukawa; Yoshiko Arai; Chiaki Iwasaki; Yoko Kinjo; Hiroshi Hotta // International Conference e-Society;2015, p340 

    In this study, we attempted to classify the massive amount of text data written in a BBS based on the extent of co-occurrence of words within each message. The concept of community in social network analysis was used for classification, and through a simulated annealing algorithm, the community...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics