Xiangyu Zhao

Identifying effective multiple spreaders by coloring complex networks

How to identify influential nodes in social networks is of theoretical significance, which relates to how to prevent epidemic spreading or cascading failure, how to accelerate information diffusion, and so on. In this Letter, we make an attempt to find \emph{effective multiple spreaders} in complex networks by generalizing the idea of the coloring problem in graph theory to complex networks. In our method, each node in a network is colored by one kind of color and nodes with the same color are sorted into an independent set. Then, for a given centrality index, the nodes with the highest centrality in an independent set are chosen as multiple spreaders. Comparing this approach with the traditional method, in which nodes with the highest centrality from the \emph{entire} network perspective are chosen, we find that our method is more effective in accelerating the spreading process and maximizing the spreading coverage than the traditional method, no matter in network models or in real social networks. Meanwhile, the low computational complexity of the coloring algorithm guarantees the potential applications of our method.

Modeling Temporal-Spatial Correlations for Crime Prediction

Crime prediction plays a crucial role in improving public security and reducing the financial loss of crimes. The vast majority of traditional algorithms performed the prediction by leveraging demographic data, which could fail to capture the dynamics of crimes in urban. In the era of big data, we have witnessed advanced ways to collect and integrate fine-grained urban, mobile, and public service data that contains various crime-related sources and rich temporal-spatial information. Such information provides better understandings about the dynamics of crimes and has potentials to advance crime prediction. In this paper, we exploit temporal-spatial correlations in urban data for crime prediction. In particular, we validate the existence of temporal-spatial correlations in crime and develop a principled approach to model these correlations into the coherent framework TCP for crime prediction. The experimental results on real-world data demonstrate the effectiveness of the proposed framework. Further experiments have been conducted to understand the importance of temporal-spatial correlations in crime prediction.

CoSoLoRec: Joint Factor Model with Content, Social, Location for Heterogeneous Point-of-Interest Recommendation

The pervasive use of Location-based Social Networks calls for more precise Point-of-Interest recommendation. The probability of a user’s visit to a target place is influenced by multiple factors. Though there are several fusion models in such fields, heterogeneous information are not considered comprehensively. To this end, we propose a novel probabilistic latent factor model by jointly considering the social correlation, geographical influence and users’ preference. To be specific, a variant of Latent Dirichlet Allocation is leveraged to extract the topics of both user and POI from reviews which is denoted as explicit interest. Then, Probabilistic Latent Factor Model is introduced to depict the implicit interest. Moreover, Kernel Density Estimation and friend-based Collaborative Filtering are leveraged to model user’s geographic allocation and social correlation respectively. Thus, we propose CoSoLoRec, a fusion framework, to ameliorate the recommendation. Experiments on two real-word datasets show the superiority of our approach over the state-of-the-art methods.

Exploring the Choice Under Conflict for Social Event Participation

Recent years have witnessed the booming of event driven SNS, which allow cyber strangers to get connected in physical world. This new business model imposes challenges for event organizers to draw event plan and predict attendance. Intuitively, these services rely on the accurate estimation of users’ preferences. However, due to various motivation of historical participation(i.e. attendance may not definitely indicate interests), traditional recommender techniques may fail to reveal the reliable user profiles. At the same time, motivated by the phenomenon that user may face to conflict of invitation (i.e. multiple invitations received simultaneously, in which only a few could be accepted), we realize that these choices may reflect real preference. Along this line, in this paper, we develop a novel conflict-choice-based model to reconstruct the decision-making process of users when facing to conflict. To be specific, in the perspective of utility in choice model, we formulate users’ tendency with integrating content, social and cost-based factors, thus topical interests as well as latent social interactions could be both captured. Furthermore, we transfer the choice of conflict-choice triples into the pairwise ranking task, and a learning-to-rank based optimization scheme is introduced to solve the problem. Comprehensive experiments on real-world data set show that our framework could outperform the state-of-the-art baselines with significant margin, which validates the hypothesis that conflict and choice could better explain user’s real preference.

Crime in Urban Areas:: A Data Mining Perspective

Urban safety and security play a crucial role in improving life quality of citizen and the sustainable development of urban. Traditional urban crime research focused on leveraging demographic data, which is insufficient to capture the complexity and dynamics of urban crimes. In the era of big data, we have witnessed advanced ways to collect and integrate fine-grained urban, mobile, and public service data that contains various crime-related sources as well as rich environmental and social information. The availability of big urban data provides unprecedented opportunities, which enable us to conduct advanced urban crime research. Meanwhile, environmental and social crime theories from criminology provide better understandings about the behaviors of offenders and complex patterns of crime in urban. They can not only help bridge the gap from what we have (big urban data) to what we want to understand about urban crime (urban crime analysis); but also guide us to build computational models for crime. In this article, we give an overview to key theories from criminology, summarize crime analysis on urban data, review state-of-the-art algorithms for various types of computational crime tasks and discuss some appealing research directions that can bring the urban crime research into a new frontier.

Exploring Transfer Learning for Crime Prediction

Crime prediction plays a crucial role in addressing crime, violence, conflict and insecurity in cities to promote good governance, appropriate urban planning and management. Plenty efforts have been made on developing crime prediction models by leveraging demographic data, but they failed to capture the dynamic nature of crimes in urban. Recently, with the development of new techniques for collecting and integrating fine-grained crime-related datasets, there is a potential to obtain better understandings about the dynamics of crimes and advance crime prediction. However, for a city, it is hard to build a uniform framework for all boroughs due to the uneven distribution of data. To this end, in this paper, we exploit spatio-temporal patterns in urban data in one borough in a city, and then leverage transfer learning techniques to reinforce the crime prediction of other boroughs. Specifically, we first validate the existence of spatio-temporal patterns in urban crime. Then we extract the crime-related features from cross-domain datasets. Finally we propose a novel transfer learning framework to integrate these features and model spatio-temporal patterns for crime prediction.