Jierui Xie

SLPA: Uncovering Overlapping Communities in Social Networks via a Speaker-Listener Interaction Dynamic Process

Overlap is one of the characteristics of social networks, in which a person may belong to more than one social group. For this reason, discovering overlapping structures is necessary for realistic social analysis. In this paper, we present a novel, general framework to detect and analyze both individual overlapping nodes and entire communities. In this framework, nodes exchange labels according to dynamic interaction rules. A specific implementation called Speaker-listener Label Propagation Algorithm (SLPA) demonstrates an excellent performance in identifying both overlapping nodes and overlapping communities with different degrees of diversity.

Social consensus through the influence of committed minorities.

We show how the prevailing majority opinion in a population can be rapidly reversed by a small fraction p of randomly distributed committed agents who consistently proselytize the opposing opinion and are immune to influence. Specifically, we show that when the committed fraction grows beyond a critical value p(c) ≈ 10%, there is a dramatic decrease in the time T(c) taken for the entire population to adopt the committed opinion. In particular, for complete graphs we show that when p < pc, T(c) ~ exp [α(p)N], whereas for p>p(c), T(c) ~ ln N. We conclude with simulation results for Erdős-Rényi random graphs and scale-free networks which show qualitatively similar behavior.

Towards linear time overlapping community detection in social networks

Membership diversity is a characteristic aspect of social networks in which a person may belong to more than one social group. For this reason, discovering overlapping structures is necessary for realistic social analysis. In this paper, we present a fast algorithm, called SLPA, for overlapping community detection in large-scale networks. SLPA spreads labels according to dynamic interaction rules. It can be applied to both unipartite and bipartite networks. It is also able to uncover overlapping nested hierarchy . The time complexity of SLPA scales linearly with the number of edges in the network. Experiments in both synthetic and real-world networks show that SLPA has an excellent performance in identifying both node and community level overlapping structures.

Community detection using a neighborhood strength driven Label Propagation Algorithm

Studies of community structure and evolution in large social networks require a fast and accurate algorithm for community detection. As the size of analyzed communities grows, complexity of the community detection algorithm needs to be kept close to linear. The Label Propagation Algorithm (LPA) has the benefits of nearly-linear running time and easy implementation, thus it forms a good basis for efficient community detection methods. In this paper, we propose new update rule and label propagation criterion in LPA to improve both its computational efficiency and the quality of communities that it detects. The speed is optimized by avoiding unnecessary updates performed by the original algorithm. This change reduces significantly (by order of magnitude for large networks) the number of iterations that the algorithm executes. We also evaluate our generalization of the LPA update rule that takes into account, with varying strength, connections to the neighborhood of a node considering a new label. Experiments on computer generated networks and a wide range of social networks show that our new rule improves the quality of the detected communities compared to those found by the original LPA. The benefit of considering positive neighborhood strength is pronounced especially on real-world networks containing sufficiently large fraction of nodes with high clustering coefficient.

LabelRank: A stabilized label propagation algorithm for community detection in networks

An important challenge in big data analysis nowadays is detection of cohesive groups in large-scale networks, including social networks, genetic networks, communication networks and so. In this paper, we propose LabelRank, an efficient algorithm detecting communities through label propagation. A set of operators is introduced to control and stabilize the propagation dynamics. These operations resolve the randomness issue in traditional label propagation algorithms (LPA), stabilizing the discovered communities in all runs of the same network. Tests on real-world networks demonstrate that LabelRank significantly improves the quality of detected communities compared to LPA, as well as other popular algorithms.

Evolution of opinions on social networks in the presence of competing committed groups.

Public opinion is often affected by the presence of committed groups of individuals dedicated to competing points of view. Using a model of pairwise social influence, we study how the presence of such groups within social networks affects the outcome and the speed of evolution of the overall opinion on the network. Earlier work indicated that a single committed group within a dense social network can cause the entire network to quickly adopt the groups opinion (in times scaling logarithmically with the network size), so long as the committed group constitutes more than about of the population (with the findings being qualitatively similar for sparse networks as well). Here we study the more general case of opinion evolution when two groups committed to distinct, competing opinions and , and constituting fractions and of the total population respectively, are present in the network. We show for stylized social networks (including Erdös-Rényi random graphs and Barabási-Albert scale-free networks) that the phase diagram of this system in parameter space consists of two regions, one where two stable steady-states coexist, and the remaining where only a single stable steady-state exists. These two regions are separated by two fold-bifurcation (spinodal) lines which meet tangentially and terminate at a cusp (critical point). We provide further insights to the phase diagram and to the nature of the underlying phase transitions by investigating the model on infinite (mean-field limit), finite complete graphs and finite sparse networks. For the latter case, we also derive the scaling exponent associated with the exponential growth of switching times as a function of the distance from the critical point.

LabelRankT: incremental community detection in dynamic networks via label propagation

An increasingly important challenge in network analysis is efficient detection and tracking of communities in dynamic networks for which changes arrive as a stream. There is a need for algorithms that can incrementally update and monitor communities whose evolution generates huge real-time data streams, such as the Internet or on-line social networks. In this paper, we propose LabelRankT, an on-line distributed algorithm for detection of communities in large-scale dynamic networks through stabilized label propagation. Results of tests on real-world networks demonstrate that LabelRankT has much lower computational costs than other algorithms. It also improves the quality of the detected communities compared to dynamic detection methods and matches the quality achieved by static detection approaches. Unlike most of other algorithms which apply only to binary networks, LabelRankT works on weighted and directed networks, which provides a flexible and promising solution for real-world applications.

Social influencing and associated random walk models: Asymptotic consensus times on the complete graph

We investigate consensus formation and the asymptotic consensus times in stylized individual- or agent-based models, in which global agreement is achieved through pairwise negotiations with or without a bias. Considering a class of individual-based models on finite complete graphs, we introduce a coarse-graining approach (lumping microscopic variables into macrostates) to analyze the ordering dynamics in an associated random-walk framework. Within this framework, yielding a linear system, we derive general equations for the expected consensus time and the expected time spent in each macro-state. Further, we present the asymptotic solutions of the 2-word naming game and separately discuss its behavior under the influence of an external field and with the introduction of committed agents.

Identifying robust communities and multi-community nodes by combining top-down and bottom-up approaches to clustering.

Biological functions are carried out by groups of interacting molecules, cells or tissues, known as communities. Membership in these communities may overlap when biological components are involved in multiple functions. However, traditional clustering methods detect non-overlapping communities. These detected communities may also be unstable and difficult to replicate, because traditional methods are sensitive to noise and parameter settings. These aspects of traditional clustering methods limit our ability to detect biological communities, and therefore our ability to understand biological functions. To address these limitations and detect robust overlapping biological communities, we propose an unorthodox clustering method called SpeakEasy which identifies communities using top-down and bottom-up approaches simultaneously. Specifically, nodes join communities based on their local connections, as well as global information about the network structure. This method can quantify the stability of each community, automatically identify the number of communities, and quickly cluster networks with hundreds of thousands of nodes. SpeakEasy shows top performance on synthetic clustering benchmarks and accurately identifies meaningful biological communities in a range of datasets, including: gene microarrays, protein interactions, sorted cell populations, electrophysiology and fMRI brain imaging.

A scale-invariant local descriptor for event recognition in 1D sensor signals

In this paper, we introduce a shape-based, time-scale invariant feature descriptor for 1-D sensor signals. The timescale invariance of the feature allows us to use feature from one training event to describe events of the same semantic class which may take place over varying time scales such as walking slow and walking fast. Therefore it requires less training set. The descriptor takes advantage of the invariant location detection in the scale space theory and employs a high level shape encoding scheme to capture invariant local features of events. Based on this descriptor, a scale-invariant classifier with “R” metric (SIC-R) is designed to recognize multi-scale events of human activities. The R metric combines the number of matches of keypoint in scale space with the Dynamic Time Warping score. SIC-R is tested on various types of 1-D sensors data from passive infrared, accelerometer and seismic sensors with more than 90% classification accuracy.