Integrating meta-path selection with user-guided object clustering in heterogeneous information networks

Sun, Yizhou; Norick, Brandon; Han, Jiawei; Yan, Xifeng; Yu, Philip S.; Yu, Xiao

doi:10.1145/2339530.2339738

Cited by 231 publications

(194 citation statements)

References 32 publications

Supporting

Mentioning

192

Contrasting

Unclassified

Order By: Relevance

“…NetClus (Sun et al 2009b), BibClus (Xu and Deng 2011) and PathSelClus (Sun et al 2012a) are three typical probabilistic generative models for clustering general heterogeneous networks. NetClus and BibClus are constrained on specific data structures.…”

Section: Related Workmentioning

confidence: 99%

A novel probabilistic clustering model for heterogeneous networks

Deng

2016

Mach Learn

View full text Add to dashboard Cite

Heterogeneous networks, consisting of multi-type objects coupled with various relations, are ubiquitous in the real world. Most previous work on clustering heterogeneous networks either converts them into homogeneous networks or simplifies the modeling of the heterogeneity in terms of specific objects, structures or assumptions. However, few studies consider all relevant objects and relations, and trade-off between integrating relevant objects and reducing the noises caused by relations across objects. In this paper, we propose a general probabilistic graphical model for clustering heterogeneous networks. First, we present a novel graphical representation based on our basic assumptions: different relation types produce different weight distributions to specify intra-cluster probability between two objects, and clusters are formed around cluster cores. Then, we derive an efficient algorithm called PROCESS, standing for PRObabilistic Clustering modEl for heterogeneouS networkS. PROCESS employs a balance-controlled message passing algorithm and mathematical programming for inference and estimation. Experimental results show that our approach is effective and significantly outperforms the state-of-the-art algorithms on both synthetic and real data from heterogeneous networks.

show abstract

Section: Related Workmentioning

confidence: 99%

A novel probabilistic clustering model for heterogeneous networks

Deng

2016

Mach Learn

View full text Add to dashboard Cite

show abstract

“…In this study, we first employ a semisupervised learning model (in the form of PathSelClus [29]) to leverage the mapping between users and their specifically accessed diagnoses of EHRs in the fine-grained data set. Then we consider a more challenging scenario where such fine-grained mapping is not available.…”

Section: Discoverymentioning

confidence: 99%

“…The structure of our data sets can be represented as a typical heterogeneous information network [28,29,31]. Therefore, we use PathSelClus [29], a state-of-theart semi-supervised learning model based on heterogeneous information networks for user-guided clustering. For context, we begin with a brief introduction to heterogeneous information networks.…”

Section: Pathselclus For Discoverymentioning

confidence: 99%

Discovering de facto diagnosis specialties

Zhang

Gunter

et al. 2015

Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics

View full text Add to dashboard Cite

In health care institutions, medical specialty information may be lacking or inaccurate, in part because there is no official code to express such specialties. Diagnosis histories offer information on which medical specialties may exist in practice, regardless of whether they have official codes. We refer to such specialties that are predicted with high certainty by diagnosis histories de facto diagnosis specialties. The objective of our research is to discover de facto diagnosis specialties under a general discovery-evaluation framework. Specifically, we employ a semi-supervised learning model (based on heterogeneous information network analysis) and an unsupervised learning method (based on topic modeling) for discovery. We further employ four supervised learning models for evaluation. We use one year of diagnosis histories from a major medical center, which consists of two data sets. One is fine-grained and has diagnoses assigned to 41,603 patients that are accessed by 2,504 medical service providers. The other is general and has diagnoses assigned to 291,562 patients that are accessed by 3,269 medical service providers. The semi-supervised learning model discovers a specialty for Breast Cancer on the fine-grained data set; while the unsupervised learning method confirms this discovery and suggests another specialty for Obesity on the larger general data set. The evaluation results reinforce that these two specialties can be recognized accurately by supervised learning models in comparison with 12 common diagnosis specialties defined by the Health Care Provider Taxonomy Code Set.

show abstract

“…However, most of the real-world networks are heterogeneous ones [4]. In KDD-2012, Sun et.al proposed PathSelClus [9], a user guided clustering method in heterogeneous information networks. PathSelClus integrates both the meta-path selection and clustering processes.…”

Section: Introductionmentioning

confidence: 99%

“…In a heterogeneous information network, two objects may be connected via different relation paths or sequences of relations [9]. These different relation paths have different semantic meanings.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised Clustering on Heterogeneous Information Networks

Luo

Pang

Wang

2014

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Abstract. Semi-supervised clustering on information networks combines both the labeled and unlabeled data sets with an aim to improve the clustering performance. However, the existing semi-supervised clustering methods are all designed for homogeneous networks and do not deal with heterogeneous ones. In this work, we propose a semi-supervised clustering approach to analyze heterogeneous information networks, which include multi-typed objects and links and may contain more useful semantic information. The major challenge in the clustering task here is how to handle multi-relations and diverse semantic meanings in heterogeneous networks. In order to deal with this challenge, we introduce the concept of relation-path to measure the similarity between two data objects of the same type. Thereafter, we make use of the labeled information to extract different weights for all relation-paths. Finally, we propose SemiRPClus, a complete framework for semi-supervised learning in heterogeneous networks. Experimental results demonstrate the distinct advantages in effectiveness and efficiency of our framework in comparison with the baseline and some state-of-the-art approaches.

show abstract

Integrating meta-path selection with user-guided object clustering in heterogeneous information networks

Cited by 231 publications

References 32 publications

A novel probabilistic clustering model for heterogeneous networks

A novel probabilistic clustering model for heterogeneous networks

Discovering de facto diagnosis specialties

Semi-supervised Clustering on Heterogeneous Information Networks

Contact Info

Product

Resources

About