A heterogeneous information network is an information network composed of multiple types of objects. Clustering on such a network may lead to better understanding of both hidden structures of the network and the individual role played by every object in each cluster. However, although clustering on homogeneous networks has been studied over decades, clustering on heterogeneous networks has not been addressed until recently. A recent study proposed a new algorithm, RankClus, for clustering on bi-typed heterogeneous networks. However, a real-world network may consist of more than two types, and the interactions among multi-typed objects play a key role at disclosing the rich semantics that a network carries. In this paper, we study clustering of multi-typed heterogeneous networks with a star network schema and propose a novel algorithm, NetClus, that utilizes links across multityped objects to generate high-quality net-clusters. An iterative enhancement method is developed that leads to effective ranking-based clustering in such heterogeneous networks. Our experiments on DBLP data show that NetClus generates more accurate clustering results than the baseline topic model algorithm PLSA and the recently proposed algorithm, RankClus. Further, NetClus generates informative clusters, presenting good ranking and cluster membership information for each attribute object in each net-cluster.

Similarity search is a primitive operation in database and Web search engines. With the advent of large-scale heterogeneous information networks that consist of multi-typed, interconnected objects, such as the bibliographic networks and social media networks, it is important to study similarity search in such networks. Intuitively, two objects are similar if they are linked by many paths in the network. However, most existing similarity measures are defined for homogeneous networks. Different semantic meanings behind paths are not taken into consideration. Thus they cannot be directly applied to heterogeneous networks. In this paper, we study similarity search that is defined among the same type of objects in heterogeneous networks. Moreover, by considering different linkage paths in a network, one could derive various similarity semantics. Therefore, we introduce the concept

This paper proposes a novel topic model, Citation-Author-Topic (CAT) model that addresses a semantic search task we define as expert search – given a research area as a query, it returns names of experts in this area. For example, Michael Collins would be one of the top names retrieved given the query Syntactic Parsing. Our contribution in this paper is two-fold. First, we model the cited author information together with words and paper authors. Such extra contextual information directly models linkage among authors and enhances the author-topic association, thus produces more coherent author-topic distribution. Second, we provide a preliminary solution to the task of expert search when the learning repository contains exclusively research related documents authored by the experts. When compared with a previous proposed model (Johri et al., 2010), the proposed model produces high quality author topic linkage and achieves over 33 % error reduction evaluated by the standard MAP measurement. 1

The prevailing of Web 2.0 techniques has led to the boom of various online communities, where topics are spreading ubiquitously among user-generated documents. Together with this diffusion process is the content evolution of the topics, where novel contents are introduced in by documents which adopt the topic. Unlike an explicit user behavior (e.g., buying a DVD), both the diffusion paths and the evolutionary process of a topic are implicit, making them much more challenging to be discovered. In this paper, we aim to simultaneously track the evolution of any arbitrary topic and reveal the latent diffusion paths of that topic in a social community. A novel and principled probabilistic model is proposed which casts our task as an joint inference problem, taking into consideration of textual documents, social influences, and topic evolution in a unified way. Specifically, a mixture model is introduced to model the generation of text according to the diffusion and the evolution of the topic, while the whole diffusion process is regularized with user-level social influences through a Gaussian Markov Random Field. Experiments on both synthetic data and real world data show that the discovery of topic diffusion and evolution benefits from this joint inference; and the probabilistic model we propose performs significantly better than existing methods.

User generated information in online communities has been characterized with the mixture of a text stream and a network structure both changing over time. A good example is a web-blogging community with the daily blog posts and a social network of bloggers. An important task of analyzing an online community is to observe and track the popular events, or topics that evolve over time in the community. Existing approaches usually focus on either the burstiness of topics or the evolution of networks, but ignoring the interplay between textual topics and network structures. In this paper, we formally define the problem of popular event tracking (PET) in online communities, focusing on the interplay between textual content and social networks. We propose a novel statistical method that models the popularity of events over time, taking into consideration the burstiness of user interest, information diffusion in the network structure, and the evolution of textual topics. Specifically, a Gibbs Random Field is defined to model the influence of historical status of actors in the network and the dependency relationships among them; thereafter a topic model generates the words in text content of the event, regularized by the Gibbs Random Field. We prove that two classical models of information diffusion and text burstiness are special cases of our model under certain conditions. Empirical experiments with two different communities and datasets (i.e., Twitter and DBLP) show that our approach is effective and outperforms existing methods.

With the rapid development of online social media, online shopping sites and cyber-physical systems, heterogeneous information networks have become increasingly popular and content-rich over time. In many cases, such networks contain multiple types of objects and links, as well as different kinds of attributes. The clustering of these objects can provide useful insights in many applications. However, the clustering of such networks can be challenging since (a) the attribute values of objects are often incomplete, which implies that an object may carry only partial attributes or even no attributes to correctly label itself; and (b) the links of different types may carry different kinds of semantic meanings, and it is a difficult task to determine the nature of their relative importance in helping the clustering for a given purpose. In this paper, we address these challenges by proposing a model-based clustering algorithm. We design a probabilistic model which clusters the objects of different types into a common hidden space, by using a user-specified set of attributes, as well as the links from different relations. The strengths of different types of links are automatically learned, and are determined by the given purpose of clustering. An iterative algorithm is designed for solving the clustering problem, in which the strengths of different types of links and the quality of clustering results mutually enhance each other. Our experimental results on real and synthetic data sets demonstrate the effectiveness and efficiency of the algorithm. 1.

Abstract—The prevalence of Web 2.0 techniques has led to the boom of various online communities, where topics spread ubiquitously among user-generated documents. Working together with this diffusion process is the evolution of topic content, where novel contents are introduced by documents which adopt the topic. Unlike explicit user behavior (e.g., buying a DVD), both the diffusion paths and the evolutionary process of a topic are implicit, making their discovery challenging. In this paper, we track the evolution of an arbitrary topic and reveal the latent diffusion paths of that topic in a social community. A novel and principled probabilistic model is proposed which casts our task as an joint inference problem, which considers textual documents, social influences, and topic evolution in a unified way. Specifically, a mixture model is introduced to model the generation of text according to the diffusion and the evolution of the topic, while the whole diffusion process is regularized with user-level social influences through a Gaussian Markov Random Field. Experiments on both synthetic data and real world data show that the discovery of topic diffusion and evolution benefits from this joint inference; and the probabilistic model we propose performs significantly better than existing methods. I.

With the development of Web applications, textual documents are not only getting richer, but also ubiquitously interconnected with users and other objects in various ways, which brings about text-rich heterogeneous information networks. Topic models have been proposed and shown to be useful for document analysis, and the interactions among multi-typed objects play a key role at disclosing the rich semantics of the network. However, most of topic models only consider the textual information while ignore the network structures or can merely integrate with homogeneous networks. None of them can handle heterogeneous information network well. In this paper, we propose a novel topic model with biased propagation (TMBP) algorithm to directly incorporate heterogeneous information network with topic modeling in a unified way. The underlying intuition is that multi-typed objects should be treated differently along with their inherent textual information and the rich semantics of the heterogeneous information network. A simple and unbiased topic propagation across such a heterogeneous network does not make much sense. Consequently, we investigate and develop two biased propagation frameworks, the biased random walk framework and the biased regularization framework, for the TMBP algorithm from different perspectives, which can discover latent topics and identify clusters of multi-typed objects simultaneously. We extensively evaluate the proposed approach and compare to the state-of-the-art techniques on several datasets. Experimental results demonstrate that the improvement in our proposed approach is consistent and promising.

Abstract—Most objects and data in the real world are interconnected, forming complex, heterogeneous but often semistructured information networks. However, many database researchers consider a database merely as a data repository that supports storage and retrieval rather than an information-rich, inter-related and multi-typed information network that supports comprehensive data analysis; whereas many network researchers focus on homogeneous networks. Departing from both, we view interconnected, semi-structured datasets as heterogeneous, information-rich networks and study how to uncover hidden knowledge in such networks. For example, a university database can be viewed as a heterogeneous information network, where objects of multiple types, such as students, professors, courses, departments, and multiple typed relationships, such as teach and advise are intertwined together, providing abundant information. In this tutorial, we present an organized picture on mining heterogeneous information networks and introduce a set of interesting, effective and scalable network mining methods. The topics to be covered include (i) database as an information network, (ii) mining information networks: clustering, classification, ranking, similarity search, and meta path-guided analysis, (iii) construction of quality, informative networks by data mining, (iv) trend and evolution analysis in heterogeneous information networks, and (v) research frontiers. We show that heterogeneous information networks are informative, and link analysis on such networks is powerful at uncovering critical knowledge hidden in large semi-structured datasets. Finally, we also present a few promising research directions. I.