Query-Based Outlier Detection in Heterogeneous Information Networks

Size: px
Start display at page:

Download "Query-Based Outlier Detection in Heterogeneous Information Networks"

Transcription

1 Query-Based Outlier Detection in Heterogeneous Information Networks Jonathan Kuck 1, Honglei Zhuang 1, Xifeng Yan 2, Hasan Cam 3, Jiawei Han 1 1 Uniersity of Illinois at Urbana-Champaign 2 Uniersity of California at Santa Barbara 3 US Army Research Lab

2 Heterogeneous information networks are networks composed of multi-typed, interconnected ertices and links Outlier detection aims to find ertices that deiate significantly from other ertices Howeer, outliers in such a heterogeneous network could be defined in many different ways E.g. Finding outlier in authors of this paper Jonathan Honglei Xifeng Hasan Jiawei

3 Heterogeneous information networks are networks composed of multi-typed, interconnected ertices and links Outlier detection aims to find ertices that deiate significantly from other ertices Howeer, outliers in such a heterogeneous network could be defined in many different ways E.g. Finding outlier in authors of this paper Jonathan Honglei Xifeng Hasan Jiawei

4 Heterogeneous information networks are networks composed of multi-typed, interconnected ertices and links Outlier detection aims to find ertices that deiate significantly from other ertices Howeer, outliers in such a heterogeneous network could be defined in many different ways E.g. Finding outlier in authors of this paper Jonathan Honglei Xifeng Hasan Jiawei As users hae their own intuition about which kind of outliers they are interested in Allow users to specify queries for outlier detection

5 Research Challenges How do users interact with the system to specify their queries? How do we define a general outlierness measure for different queries? How to efficiently find outliers for different queries?

6 Outline Basic Concepts and Notations Outlier Query Language NetOut: Outlierness Measure Processing Outlier Queries Experimental Results Summary

7 Basic Concepts and Notations Heterogeneous Information Network An information network with multiple types of ertices G V, E,, T where V is the set of ertices; E is the set of edges; T is the set of types, and : V T assigns each ertex a type. Network schema An instantiated network

8 Basic Concepts and Notations Meta-Path An ordered sequence of ertex types, denoted as E.g. P Author,Paper,Venue Meta-Path Instantiation Use P i, j to denote paths between two ertices with the types that align with the gien meta-path E.g. Zoe, KDD is shown below in red solid lines P P P, i j Network schema An instantiated network

9 Basic Concepts and Notations Neighborhood Based on a meta-path P, defined as E.g. N P Zoe KDD, ICDE Neighbor Vector, N P i j P i j Based on a meta-path P, the neighbor ector P i describes how many paths there are from i to each of its neighbors E.g. Zoe KDD:3, ICDE:2 P Network schema An instantiated network

10 Formalization of Outlier Queries Gien a heterogeneous information network A query can be formalized as where Q S, S, Pw, c S V is a set of (same-typed) candidate ertices c Specifying from where outliers are chosen from S V is a set of (same-typed) reference ertices r Specifying a sample of normal ertices Optional. By default it equals to the candidate set Pw, define a weighted set of meta-paths Specifying how two ertices are compared r

11 Outlier Query Language General Formulation FIND OUTLIERS FROM author{ C. Faloutsos }.paper.author COMPARE TO enue { KDD }.paper.author JUDGED BY author.paper.enue TOP 10;

12 Outlier Query Language General Formulation FIND OUTLIERS FROM author{ C. Faloutsos }.paper.author Specifying the candidate set Sc NPC. Faloutsos P Author, Paper, Author COMPARE TO enue { KDD }.paper.author JUDGED BY author.paper.enue TOP 10;

13 Outlier Query Language General Formulation FIND OUTLIERS Specifying the candidate set FROM author{ C. Faloutsos }.paper.author COMPARE TO enue { KDD }.paper.author Specifying the reference set JUDGED BY author.paper.enue TOP 10; Sr NPKDD P Venue, Paper, Author

14 Outlier Query Language General Formulation FIND OUTLIERS Specifying the candidate set FROM author{ C. Faloutsos }.paper.author COMPARE TO enue { KDD }.paper.author JUDGED BY author.paper.enue Compare ertices by neighbor ector where TOP 10; P P Author, Paper, Venue i Specifying the reference set

15 Outlier Query Language General Formulation FIND OUTLIERS Specifying the candidate set FROM author{ C. Faloutsos }.paper.author COMPARE TO enue { KDD }.paper.author JUDGED BY author.paper.enue TOP 10; Only return top 10 outliers Specifying how ertices are compared Specifying the reference set

16 Outlier Query Language (cont ) Allow complicated judging standards E.g. multiple weighted neighbor ectors JUDGED BY author.paper.enue: 0.6, author.paper.author: 0.4 Allow operations on sets E.g. select by conditions FROM enue { KDD }.paper.author AS A WHERE COUNT(A.paper)> 10

17 NetOut: A General Network-Based Outlierness Measure P Gien a meta-path (in JUDGED BY clause) Define the connectiity between two ertices, 1, i j PP i j The more paths between them, the more similar they are Define relatie connectiity Compare the connectiity to self-connectiity, i j 1 i, PP j 1 i, PP i Use self-connectiity as a expected connectiity to measure whether two ertices are unexpectedly connected or unexpectedly disconnected Outlier Measure: NetOut, i i j S j r

18 Comparing NetOut to Other Measures A toy example. Neighbor Vector VLDB KDD STOC SIGGRAPH Reference Author(s) Sarah Rob Lucy *Joe *Emma Outlier measure comparison. The lower alue, the more likely to be an outlier. NetOut PathSim [1] CosSim Sarah Rob Lucy Joe Emma Joe is not necessarily an interesting outlier, as those papers might simply be noise Emma is obiously an outlier and should be assigned a lower alue [1] Sun, Yizhou, et al. "PathSim: Meta path-based top-k similarity search in heterogeneous information networks." VLDB 2011.

19 Comparison on Real Data Set Apply on network constructed from DBLP data set Find outliers among Christos Faloutsos coauthors, in terms of their publishing enues authors with ery few paper; uninteresting outliers

20 Query Processing The calculation of NetOut can be written as 2 2, ;,,, 1, j r j r j r i j i S i i i j S i i i j S i Q

21 Query Processing The calculation of NetOut can be written as Time complexity: 2 2, ;,,, 1, j r j r j r i j i S i i i j S i i i j S i Q O( S r ), only calculated once O( S c ), calculate oer all the candidate ertices c r O S S

22 Pre-Materialization of Meta-Path We obsere Calculation of outlierness only has time complexity of O S S Retrieing i for each ertex is much more time consuming Pre-materialization c Pre-store the materialization of all the length-2 meta-paths r

23 Selectie Pre-Materialization Storing materialization of all length-2 metapaths can be space-consuming Selectie Pre-materialization From a gien set of training queries, take ertices that frequently appear in the candidate sets (e.g. those appear in more than 10% of queries) Pre-materialize all the length-2 meta-paths for these frequently appearing ertices

24 Experimental Setup Data Set DBLP Data Set 2,244,018 publications, 1,274,360 authors Construct the network according to the schema aboe Publishing enue information is included Terms are extracted from publication titles Query Sets Design three different types of queries to find different kinds of outliers Generate 10,000 random queries for each type of queries as a query set

25 Case Study With different queries, the outlier measure is able to capture different outliers accordingly E.g. Finding outliers in Christos Faloutsos coauthors Outlier results by comparing publishing enues Outlier results by comparing coauthor communities

26 Efficiency Study Comparing strategies Baseline: No pre-materialization Pre-Materialization (PM): All length-2 meta-path instantiations are pre-computed and indexed Selectie Pre-Materialization (SPM): Only a subset of instantiations with relatie frequency larger than 0.01 are indexed

27 Parameter Studies for SPM Different thresholds for selectie pre-materialization

28 Summary Propose a framework for query-based outlier detection in heterogeneous information networks Formalize the definition of a query and proide a query language for users to interact with the system Design a general outlierness measure NetOut which can effectiely find interesting outliers Present an efficient implementation to process such queries

29 Thank you Introduction Outlier Query Language NetOut Measure Query Processing Experimental Results

30

Mining Query-Based Subnetwork Outliers in Heterogeneous Information Networks

Mining Query-Based Subnetwork Outliers in Heterogeneous Information Networks Mining Query-Based Subnetwork Outliers in Heterogeneous Information Networks Honglei Zhuang, Jing Zhang 2, George Brova, Jie Tang 2, Hasan Cam 3, Xifeng Yan 4, Jiawei Han University of Illinois at Urbana-Champaign

More information

User Guided Entity Similarity Search Using Meta-Path Selection in Heterogeneous Information Networks

User Guided Entity Similarity Search Using Meta-Path Selection in Heterogeneous Information Networks User Guided Entity Similarity Search Using Meta-Path Selection in Heterogeneous Information Networks Xiao Yu, Yizhou Sun, Brandon Norick, Tiancheng Mao, Jiawei Han Computer Science Department University

More information

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks Yu Shi, Huan Gui, Qi Zhu, Lance Kaplan, Jiawei Han University of Illinois at Urbana-Champaign (UIUC) Facebook Inc. U.S. Army Research

More information

AC-Close: Efficiently Mining Approximate Closed Itemsets by Core Pattern Recovery

AC-Close: Efficiently Mining Approximate Closed Itemsets by Core Pattern Recovery : Efficiently Mining Approximate Closed Itemsets by Core Pattern Recovery Hong Cheng Philip S. Yu Jiawei Han University of Illinois at Urbana-Champaign IBM T. J. Watson Research Center {hcheng3, hanj}@cs.uiuc.edu,

More information

GRAPH THEORY LECTURE 3 STRUCTURE AND REPRESENTATION PART B

GRAPH THEORY LECTURE 3 STRUCTURE AND REPRESENTATION PART B GRAPH THEORY LECTURE 3 STRUCTURE AND REPRESENTATION PART B Abstract. We continue 2.3 on subgraphs. 2.4 introduces some basic graph operations. 2.5 describes some tests for graph isomorphism. Outline 2.3

More information

QANet: Tensor Decomposition Approach for Query-based Anomaly Detection in Heterogeneous Information Networks

QANet: Tensor Decomposition Approach for Query-based Anomaly Detection in Heterogeneous Information Networks QANet: Tensor Decomposition Approach for Query-based Anomaly Detection in Heterogeneous Information Networks Vahid Ranjbar, Mostafa Salehi, Pegah Jandaghi, and Mahdi Jalili, Senior Member, IEEE Abstract

More information

Week 9-10: Connectivity

Week 9-10: Connectivity Week 9-0: Connectiity October 3, 206 Vertex Connectiity Let G = (V, E) be a graph. Gien two ertices x, y V. Two (x, y)-path are said to be internally disjoint if they hae no internal ertices in common.

More information

Mining Trusted Information in Medical Science: An Information Network Approach

Mining Trusted Information in Medical Science: An Information Network Approach Mining Trusted Information in Medical Science: An Information Network Approach Jiawei Han Department of Computer Science University of Illinois at Urbana-Champaign Collaborated with many, especially Yizhou

More information

Modification Semantics in Now-Relative Databases

Modification Semantics in Now-Relative Databases Modification Semantics in Now-Relatie Databases Kristian Torp Christian S. Jensen Richard T. Snodgrass February 5, 00 Abstract Most real-world databases record time-arying information. In such databases,

More information

A Bit-Window based Algorithm for Balanced and Efficient Object Placement and Lookup in Large-scale Object Based Storage Cluster

A Bit-Window based Algorithm for Balanced and Efficient Object Placement and Lookup in Large-scale Object Based Storage Cluster A Bit-Window based Algorithm for Balanced and Efficient Object lacement and Lookup in Large-scale Object Based Storage Cluster enuga Kanagaelu A*STA Data Storage Institute, Singapore Email:renuga_KANAGAVELU@dsia-staredusg

More information

Data Mining: Dynamic Past and Promising Future

Data Mining: Dynamic Past and Promising Future SDM@10 Anniversary Panel: Data Mining: A Decade of Progress and Future Outlook Data Mining: Dynamic Past and Promising Future Jiawei Han Department of Computer Science University of Illinois at Urbana

More information

CERIAS Tech Report

CERIAS Tech Report CERIAS Tech Report 2001-68 The Effect of Matching Watermark and Compression Transforms in Compressed Color Images by Raymond B. Wolfgang and Christine I. Podilchuk and Edward J. Delp Center for Education

More information

A dimension-independent simplicial data structure for non-manifold shapes

A dimension-independent simplicial data structure for non-manifold shapes A dimension-independent simplicial data structure for non-manifold shapes Annie Hui Dept of Computer Science, Unierity of Maryland, College Park, USA e-mail:huiannie@cs.umd.edu Leila De Floriani Dept of

More information

Motion Compensated Frame Interpolation Using Motion Vector Refinement with Low Complexity

Motion Compensated Frame Interpolation Using Motion Vector Refinement with Low Complexity Motion Compensated Frame Interpolation Using Motion Vector Refinement with Low Complexity Jun-Geon Kim and Daeho Lee Abstract-- In this paper, we propose a noel method of motion compensated frame interpolation

More information

Selective Refinement Of Progressive Meshes Using Vertex Hierarchies

Selective Refinement Of Progressive Meshes Using Vertex Hierarchies Selectie Refinement Of Progressie Meshes Using Vertex Hierarchies Yigang Wanga, Bernd Fröhlichb and Martin Göbelc a,c Fraunhofer-Institut für Medienkommunication, Germany b Bauhaus-Uniersität Weimar, Germany

More information

International Journal of Multidisciplinary Research and Modern Education (IJMRME) Impact Factor: 6.725, ISSN (Online):

International Journal of Multidisciplinary Research and Modern Education (IJMRME) Impact Factor: 6.725, ISSN (Online): COMPUTER REPRESENTATION OF GRAPHS USING BINARY LOGIC CODES IN DISCRETE MATHEMATICS S. Geetha* & Dr. S. Jayakumar** * Assistant Professor, Department of Mathematics, Bon Secours College for Women, Villar

More information

Modification Semantics in Now-Relative Databases

Modification Semantics in Now-Relative Databases 5 Modification Semantics in Now-Relatie Databases Kristian Torp, Christian S. Jensen, and Richard T. Snodgrass Most real-world databases record time-arying information. In such databases, the notion of

More information

Heterogeneous Graph-Based Intent Learning with Queries, Web Pages and Wikipedia Concepts

Heterogeneous Graph-Based Intent Learning with Queries, Web Pages and Wikipedia Concepts Heterogeneous Graph-Based Intent Learning with Queries, Web Pages and Wikipedia Concepts Xiang Ren, Yujing Wang, Xiao Yu, Jun Yan, Zheng Chen, Jiawei Han University of Illinois, at Urbana Champaign MicrosoD

More information

Intuitive and Interactive Query Formulation to Improve the Usability of Query Systems for Heterogeneous Graphs

Intuitive and Interactive Query Formulation to Improve the Usability of Query Systems for Heterogeneous Graphs Intuitive and Interactive Query Formulation to Improve the Usability of Query Systems for Heterogeneous Graphs Nandish Jayaram University of Texas at Arlington PhD Advisors: Dr. Chengkai Li, Dr. Ramez

More information

THE RESEARCH ON LPA ALGORITHM AND ITS IMPROVEMENT BASED ON PARTIAL INFORMATION

THE RESEARCH ON LPA ALGORITHM AND ITS IMPROVEMENT BASED ON PARTIAL INFORMATION THE RESEARCH O LPA ALGORITHM AD ITS IMPROVEMET BASED O PARTIAL IFORMATIO 1 SHEG XI 1 School of Finance, Shandong Polytechnic Uniersity, Jinan, 250353 China ABSTRACT With the growing expansion of data size,

More information

Fast Inbound Top- K Query for Random Walk with Restart

Fast Inbound Top- K Query for Random Walk with Restart Fast Inbound Top- K Query for Random Walk with Restart Chao Zhang, Shan Jiang, Yucheng Chen, Yidan Sun, Jiawei Han University of Illinois at Urbana Champaign czhang82@illinois.edu 1 Outline Background

More information

Citation Prediction in Heterogeneous Bibliographic Networks

Citation Prediction in Heterogeneous Bibliographic Networks Citation Prediction in Heterogeneous Bibliographic Networks Xiao Yu Quanquan Gu Mianwei Zhou Jiawei Han University of Illinois at Urbana-Champaign {xiaoyu1, qgu3, zhou18, hanj}@illinois.edu Abstract To

More information

IBM VisualAge for Java,Version3.5. Data Access Beans

IBM VisualAge for Java,Version3.5. Data Access Beans IBM VisualAge for Jaa,Version3.5 Data Access Beans Note! Before using this information and the product it supports, be sure to read the general information under Notices. Edition notice This edition applies

More information

Personalized Entity Recommendation: A Heterogeneous Information Network Approach

Personalized Entity Recommendation: A Heterogeneous Information Network Approach Personalized Entity Recommendation: A Heterogeneous Information Network Approach Xiao Yu, Xiang Ren, Yizhou Sun, Quanquan Gu, Bradley Sturt, Urvashi Khandelwal, Brandon Norick, Jiawei Han University of

More information

Minimum Spanning Tree in Fuzzy Weighted Rough Graph

Minimum Spanning Tree in Fuzzy Weighted Rough Graph International Journal of Engineering Research and Deelopment ISSN: 2278-067X, Volume 1, Issue 10 (June 2012), PP.23-28 www.ijerd.com Minimum Spanning Tree in Fuzzy Weighted Rough Graph S. P. Mohanty 1,

More information

Expertise-Based Data Access in Content-Centric Mobile Opportunistic Networks

Expertise-Based Data Access in Content-Centric Mobile Opportunistic Networks Expertise-Based Data Access in Content-Centric Mobile Opportunistic Networks Jing Zhao, Xiaomei Zhang, Guohong Cao, Mudhakar Sriatsa and Xifeng Yan Pennsylania State Uniersity, Uniersity Park, PA IBM T.

More information

Behavior Query Discovery in System-Generated Temporal Graphs

Behavior Query Discovery in System-Generated Temporal Graphs Behavior Query Discovery in System-Generated Temporal Graphs Bo Zong,, Xusheng Xiao, Zhichun Li, Zhenyu Wu, Zhiyun Qian, Xifeng Yan, Ambuj K. Singh, Guofei Jiang UC Santa Barbara NEC Labs, America UC Riverside

More information

Quadrilateral Meshes with Provable Angle Bounds

Quadrilateral Meshes with Provable Angle Bounds Quadrilateral Meshes with Proable Angle Bounds F. Betul Atalay Suneeta Ramaswami Dianna Xu March 3, 2011 Abstract In this paper, we present an algorithm that utilizes a quadtree data structure to construct

More information

Unsupervised Rank Aggregation with Distance-Based Models

Unsupervised Rank Aggregation with Distance-Based Models Unsupervised Rank Aggregation with Distance-Based Models Alexandre Klementiev, Dan Roth, and Kevin Small University of Illinois at Urbana-Champaign Motivation Consider a panel of judges Each (independently)

More information

Shaded Rendering and Shadow Computation for Polyhedral Animation

Shaded Rendering and Shadow Computation for Polyhedral Animation 175 Shaded Rendering and Shadow Computation for Polyhedral Animation W. Brent Seales Charles R. Dyer Department of Computer Science Uniersity of Wisconsin Madison, Wisconsin 53706 USA Abstract In this

More information

Integrating Meta-Path Selection with User-Preference for Top-k Relevant Search in Heterogeneous Information Networks

Integrating Meta-Path Selection with User-Preference for Top-k Relevant Search in Heterogeneous Information Networks Integrating Meta-Path Selection with User-Preference for Top-k Relevant Search in Heterogeneous Information Networks Shaoli Bu bsl89723@gmail.com Zhaohui Peng pzh@sdu.edu.cn Abstract Relevance search in

More information

3D TOPOLOGY FOR MODELLING OF URBAN STRUCTURES

3D TOPOLOGY FOR MODELLING OF URBAN STRUCTURES 3D TOPOLOGY FOR MODELLING OF URBAN STRUCTURES Tarun Ghawana & Sisi Zlatanoa Delft Uniersity of Technology Challenge the future Increased awareness of underground information Ludig Emgard Jakob Beetz 2

More information

Subspace Discovery for Promotion: A Cell Clustering Approach

Subspace Discovery for Promotion: A Cell Clustering Approach Subspace Discovery for Promotion: A Cell Clustering Approach Tianyi Wu and Jiawei Han University of Illinois at Urbana-Champaign, USA {twu5,hanj}@illinois.edu Abstract. The promotion analysis problem has

More information

Graph Classification in Heterogeneous

Graph Classification in Heterogeneous Title: Graph Classification in Heterogeneous Networks Name: Xiangnan Kong 1, Philip S. Yu 1 Affil./Addr.: Department of Computer Science University of Illinois at Chicago Chicago, IL, USA E-mail: {xkong4,

More information

Precise Multi-Frame Motion Estimation and Its Applications

Precise Multi-Frame Motion Estimation and Its Applications Precise Multi-Frame Motion Estimation and Its Applications Peyman Milanfar EE Department Uniersity of California, Santa Cruz milanfar@ee.ucsc.edu Joint wor with Dir Robinson, Michael Elad, Sina Farsiu

More information

Proceedings of the 34th Hawaii International Conference on System Sciences

Proceedings of the 34th Hawaii International Conference on System Sciences Network Models: Growth, Dynamics, and Failure Sandip Roy Chalee Asaathiratham Bernard C. Lesieutre George C. Verghese Massachusetts Institute of Technology Abstract This paper reports on preliminary explorations,

More information

A Modified Tabu Search Algorithm to Solve Vehicle Routing Problem

A Modified Tabu Search Algorithm to Solve Vehicle Routing Problem Journal of Computers Vol. 29 No. 3, 2018, pp. 197-209 doi:10.3966/199115992018062903019 A Modified Tabu Search Algorithm to Sole Vehicle Routing Problem Qinhong Fu 1, Kang Zhou 1*, Huaqing Qi 2, Falin

More information

B-Spline and NURBS Surfaces CS 525 Denbigh Starkey. 1. Background 2 2. B-Spline Surfaces 3 3. NURBS Surfaces 8 4. Surfaces of Rotation 9

B-Spline and NURBS Surfaces CS 525 Denbigh Starkey. 1. Background 2 2. B-Spline Surfaces 3 3. NURBS Surfaces 8 4. Surfaces of Rotation 9 B-Spline and NURBS Surfaces CS 525 Denbigh Starkey 1. Background 2 2. B-Spline Surfaces 3 3. NURBS Surfaces 8 4. Surfaces of Rotation 9 1. Background In my preious notes I e discussed B-spline and NURBS

More information

Chapter 1 Introduction

Chapter 1 Introduction Chapter 1 Introduction Abstract In this chapter, we introduce some basic concepts and definitions in heterogeneous information network and compare the heterogeneous information network with other related

More information

Topology-based Transfer Function Design

Topology-based Transfer Function Design Topology-based Transfer Function Design Gunther H. Weber, Gerik Scheuermann AG Graphische Datenerarbeitung und Computergeometrie, FB Informatik, Uniersity of Kaiserslautern, Erwin-Schrödinger-Straße, 67663

More information

A Dimension-Independent Data Structure for Simplicial Complexes

A Dimension-Independent Data Structure for Simplicial Complexes A Dimension-Independent Data Structure for Simplicial Complexes Leila De Floriani 1, Annie Hui 2, Daniele Panozzo 1, and Daid Canino 1 1 Department of Computer Science, Uniersity of Genoa, Italy deflo@disi.unige.it,

More information

c 2014 by Xiao Yu. All rights reserved.

c 2014 by Xiao Yu. All rights reserved. c 2014 by Xiao Yu. All rights reserved. ENTITY RECOMMENDATION AND SEARCH IN HETEROGENEOUS INFORMATION NETWORKS BY XIAO YU DISSERTATION Submitted in partial fulfillment of the requirements for the degree

More information

Collective Fraud Detection Capturing Inter-Transaction Dependency

Collective Fraud Detection Capturing Inter-Transaction Dependency Proceedings of Machine Learning Research 71:66 75, 2017 KDD 2017: Workshop on Anomaly Detection in Finance Collective Fraud Detection Capturing Inter-Transaction Dependency Bokai Cao Department of Computer

More information

Fast Discovery of Sequential Patterns Using Materialized Data Mining Views

Fast Discovery of Sequential Patterns Using Materialized Data Mining Views Fast Discovery of Sequential Patterns Using Materialized Data Mining Views Tadeusz Morzy, Marek Wojciechowski, Maciej Zakrzewicz Poznan University of Technology Institute of Computing Science ul. Piotrowo

More information

Meta-path based Multi-Network Collective Link Prediction

Meta-path based Multi-Network Collective Link Prediction Meta-path based Multi-Network Collective Link Prediction Jiawei Zhang Big Data and Social Computing (BDSC) Lab University of Illinois at Chicago Chicago, IL, USA jzhan9@uic.edu Philip S. Yu Big Data and

More information

On Graph Query Optimization in Large Networks

On Graph Query Optimization in Large Networks On Graph Query Optimization in Large Networks Peixiang Zhao, Jiawei Han Department of omputer Science University of Illinois at Urbana-hampaign pzhao4@illinois.edu, hanj@cs.uiuc.edu September 14th, 2010

More information

An Efficient Mesh Simplification Method with Feature Detection for Unstructured Meshes and Web Graphics

An Efficient Mesh Simplification Method with Feature Detection for Unstructured Meshes and Web Graphics An Eicient Mesh Simpliication Method with Feature Detection or Unstructured Meshes and Web Graphics Bing-Yu Chen National Taiwan Uniersity robin@im.ntu.edu.tw Tomoyuki Nishita The Uniersity o Tokyo nis@is.s.u-tokyo.ac.jp

More information

Anti-magic labellings of a class of planar graphs

Anti-magic labellings of a class of planar graphs AUSTRALASIAN JOURNAL OF COMBINATORICS Volume 41 (2008), Pages 283 290 Anti-magic labellings of a class of planar graphs V.Ch. Venkaiah K. Ramanjaneyulu Department of Mathematics S C R Engineering College

More information

WE know that most real systems usually consist of a

WE know that most real systems usually consist of a IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 29, NO. 1, JANUARY 2017 17 A Survey of Heterogeneous Information Network Analysis Chuan Shi, Member, IEEE, Yitong Li, Jiawei Zhang, Yizhou Sun,

More information

SeqIndex: Indexing Sequences by Sequential Pattern Analysis

SeqIndex: Indexing Sequences by Sequential Pattern Analysis SeqIndex: Indexing Sequences by Sequential Pattern Analysis Hong Cheng Xifeng Yan Jiawei Han Department of Computer Science University of Illinois at Urbana-Champaign {hcheng3, xyan, hanj}@cs.uiuc.edu

More information

Virtual Web Based Personalized PageRank Updating

Virtual Web Based Personalized PageRank Updating Virtual Web Based Personalized PageRank pdating Bo Song Department of Electrical Engineering and Computer Science niersity of Missouri-Columbia Columbia, Missouri bosong@mail.missouri.edu Xiaobo Jiang

More information

Camera Self-calibration Based on the Vanishing Points*

Camera Self-calibration Based on the Vanishing Points* Camera Self-calibration Based on the Vanishing Points* Dongsheng Chang 1, Kuanquan Wang 2, and Lianqing Wang 1,2 1 School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001,

More information

Polynomial Value Iteration Algorithms for Deterministic MDPs

Polynomial Value Iteration Algorithms for Deterministic MDPs Polynomial Value Iteration Algorithms for Deterministic MDPs Omid Madani Department of Computing Science Uniersity of Alberta Edmonton, AL Canada T6G 2E8 madani@cs.ualberta.ca Abstract Value iteration

More information

IVIS: SEARCH AND VISUALIZATION ON HETEROGENEOUS INFORMATION NETWORKS YINTAO YU THESIS

IVIS: SEARCH AND VISUALIZATION ON HETEROGENEOUS INFORMATION NETWORKS YINTAO YU THESIS c 2010 Yintao Yu IVIS: SEARCH AND VISUALIZATION ON HETEROGENEOUS INFORMATION NETWORKS BY YINTAO YU THESIS Submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer

More information

A Timing-constrained Simultaneous Global Routing Algorithm

A Timing-constrained Simultaneous Global Routing Algorithm A Timing-constrained Simultaneous Global Routing Algorithm Jiang Hu and Sachin S. Sapatnekar {jhu, sachin}@mail.ece.umn.edu Department of Electrical and Computer Engineering Uniersity of Minnesota Minneapolis,

More information

Calibration and Rectification for Reflection Stereo

Calibration and Rectification for Reflection Stereo Calibration and Rectification for Reflection Stereo Masao Shimizu and Masatoshi kutomi Tokyo Institute of Technology, Japan Abstract This paper presents a calibration and rectification method for single-camera

More information

Fixed Parameter Algorithms for Minimum Weight Partitions

Fixed Parameter Algorithms for Minimum Weight Partitions Fixed Parameter lgorithms for Minimum Weight Partitions Christian orgelt, Magdalene Grantson, and Christos Lecopoulos bstract In this paper we propose to sole two hard geometric optimization problems:

More information

Information Management course

Information Management course Università degli Studi di Milano Master Degree in Computer Science Information Management course Teacher: Alberto Ceselli Lecture 05(b) : 23/10/2012 Data Mining: Concepts and Techniques (3 rd ed.) Chapter

More information

HetPathMine: A Novel Transductive Classification Algorithm on Heterogeneous Information Networks

HetPathMine: A Novel Transductive Classification Algorithm on Heterogeneous Information Networks HetPathMine: A Novel Transductive Classification Algorithm on Heterogeneous Information Networks Chen Luo 1,RenchuGuan 1, Zhe Wang 1,, and Chenghua Lin 2 1 College of Computer Science and Technology, Jilin

More information

CORECLUSTER: A Degeneracy Based Graph Clustering Framework

CORECLUSTER: A Degeneracy Based Graph Clustering Framework CORECLUSTER: A Degeneracy Based Graph Clustering Framework Christos Giatsidis École Polytechnique giatsidis@lix.polytechnique.fr Fragkiskos D. Malliaros École Polytechnique fmalliaros@lix.polytechnique.fr

More information

International Journal of Computer Theory and Engineering, Vol. 1, No.2,June Vague Metagraph

International Journal of Computer Theory and Engineering, Vol. 1, No.2,June Vague Metagraph Vague Metagraph Deepti Gaur Aditya Shastri Author Ranjit Biswas and D. Seema Gaur Abstract Aim In this paper the we introduce a new concept of ague metagraph in field of ague theory. Authors presented

More information

2009 Conference for Visual Media Production

2009 Conference for Visual Media Production 009 Conference for Visual Media Production COECTIG SHAPESS VAIATIOS I STEEO IMAGE PAIS C. Doutre and P. asiopoulos Departement of Electrical and Computer gineering Uniersity of British Columbia, Vancouer,

More information

Algorithms for Model Checking (2IW55)

Algorithms for Model Checking (2IW55) Algorithms for Model Checking (2IW55) Lecture 13 The Small Progress Measures algorithm for Parity games Background material: Small Progress Measures for Soling Parity Games, Marcin Jurdzinski January 7,

More information

Motivation: Art gallery problem. Polygon decomposition. Art gallery problem: upper bound. Art gallery problem: lower bound

Motivation: Art gallery problem. Polygon decomposition. Art gallery problem: upper bound. Art gallery problem: lower bound CG Lecture 3 Polygon decomposition 1. Polygon triangulation Triangulation theory Monotone polygon triangulation 2. Polygon decomposition into monotone pieces 3. Trapezoidal decomposition 4. Conex decomposition

More information

Hidden Line and Surface

Hidden Line and Surface Copyright@00, YZU Optimal Design Laboratory. All rights resered. Last updated: Yeh-Liang Hsu (00--). Note: This is the course material for ME550 Geometric modeling and computer graphics, Yuan Ze Uniersity.

More information

The azimuth-dependent offset-midpoint traveltime pyramid in 3D HTI media

The azimuth-dependent offset-midpoint traveltime pyramid in 3D HTI media The azimuth-dependent offset-midpoint traeltime pyramid in 3D HTI media Item Type Conference Paper Authors Hao Qi; Stoas Alexey; Alkhalifah Tariq Ali Eprint ersion Publisher's Version/PDF DOI.9/segam3-58.

More information

Jing Gao 1, Feng Liang 1, Wei Fan 2, Chi Wang 1, Yizhou Sun 1, Jiawei i Han 1 University of Illinois, IBM TJ Watson.

Jing Gao 1, Feng Liang 1, Wei Fan 2, Chi Wang 1, Yizhou Sun 1, Jiawei i Han 1 University of Illinois, IBM TJ Watson. Jing Gao 1, Feng Liang 1, Wei Fan 2, Chi Wang 1, Yizhou Sun 1, Jiawei i Han 1 University of Illinois, IBM TJ Watson Debapriya Basu Determine outliers in information networks Compare various algorithms

More information

Overview. Understanding the Workload. Physical Database Design And Database Tuning. Chapter 20

Overview. Understanding the Workload. Physical Database Design And Database Tuning. Chapter 20 Physical Database Design And Database Tuning Chapter 20 Database Management Systems, R. Ramakrishnan and J. Gehrke 1 Oeriew After ER design, schema refinement, and the definition of iews, we hae the conceptual

More information

Piecewise Smooth Surface Reconstruction

Piecewise Smooth Surface Reconstruction Piecewise Smooth Surface Reconstruction Hugues Hoppe Tony DeRose Tom Duchamp y Mark Halstead z Hubert Jin x John McDonald x Jean Schweitzer Werner Stuetzle x Uniersity of Washington Seattle, WA 9895 Abstract

More information

Efficient Topological Exploration

Efficient Topological Exploration Efficient Topological Exploration Ioannis M. Rekleitis Vida Dujmoić Gregory Dudek Centre for Intelligent Machines, School of Computer Science, McGill Uniersity, 3480 Uniersity St., Montreal, Québec, Canada

More information

Spherical Barycentric Coordinates

Spherical Barycentric Coordinates Eurographics Symposium on Geometry Processing (6) Konrad Polthier, Alla Sheffer (Editors) Spherical Barycentric Coordinates Torsten Langer, Alexander Belyae, Hans-Peter Seidel MPI Informatik Abstract We

More information

Trust-Based Recommendation: an Empirical Analysis

Trust-Based Recommendation: an Empirical Analysis rust-based Recommendation: an Empirical Analysis Daire O Doherty Uniersite catholique de Louain 1348 Louain-La-Neue, Belgium daire.odoherty@student.uclouain.be Salim Jouili EURA NOVA Rue Emile Francqui,

More information

On secret sharing for graphs Draft version

On secret sharing for graphs Draft version On secret sharing for graphs Draft ersion KAMIL KULESZA, ZBIGNIEW KOTULSKI Institute of Fundamental Technological Research, Polish Academy of Sciences ul.świętokrzyska, -49, Warsaw, Poland, e-mail: {kkulesza,zkotulsk}@ippt.go.pl

More information

Which Null-Invariant Measure Is Better? Which Null-Invariant Measure Is Better?

Which Null-Invariant Measure Is Better? Which Null-Invariant Measure Is Better? Which Null-Invariant Measure Is Better? D 1 is m,c positively correlated, many null transactions D 2 is m,c positively correlated, little null transactions D 3 is m,c negatively correlated, many null transactions

More information

MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding

MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding Daokun Zhang 1, Jie Yin 2, Xingquan Zhu 3, and Chengqi Zhang 1 1 Centre for Artificial Intelligence, FEIT, University of Technology

More information

Vertex Neighborhoods, Low Conductance Cuts, and Good Seeds for Local Community Methods

Vertex Neighborhoods, Low Conductance Cuts, and Good Seeds for Local Community Methods Vertex Neighborhoods, Low Conductance Cuts, and Good Seeds for Local Community Methods Daid F. Gleich Purdue Uniersity Computer Science Department dgleich@purdue.edu C. Seshadhri Sandia National Laboratories

More information

Ioannis Stamos and Peter K. Allen. Department of Computer Science, Columbia University, New York, NY fistamos,

Ioannis Stamos and Peter K. Allen. Department of Computer Science, Columbia University, New York, NY fistamos, Interactie Sensor Planning Λ IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, 1998, pages 489-494 Ioannis Stamos and Peter K. Allen Department of Computer Science, Columbia Uniersity,

More information

A Graph Kernel Based on the Jensen-Shannon Representation Alignment

A Graph Kernel Based on the Jensen-Shannon Representation Alignment Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015) A raph Kernel Based on the Jensen-Shannon Representation Alignment Lu Bai 1,2, Zhihong Zhang 3, Chaoyan

More information

HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks

HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,, VOL. 6, NO. 1, JANUARY 2007 1 HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks Chuan Shi, Member, IEEE, Xiangnan Kong,

More information

arxiv: v2 [math.dg] 5 Jun 2018

arxiv: v2 [math.dg] 5 Jun 2018 A GEOMETRIC DESCRIPTION OF DISCRETE EXTERIOR CALCULUS FOR GENERAL TRIANGULATIONS HUMBERTO ESQUEDA, RAFAEL HERRERA, SALVADOR BOTELLO, AND MIGUEL ANGEL MORELES arxi:1802.011582 [math.dg] 5 Jun 2018 Abstract.

More information

BIQUADRATIC UNIFORM B-SPLINE SURFACE REFINEMENT

BIQUADRATIC UNIFORM B-SPLINE SURFACE REFINEMENT On-Line Geometric Modeling Notes BIQUADRATIC UNIFORM B-SPLINE SURFACE REFINEMENT Kenneth I. Joy Visualization and Graphics Research Group Department of Computer Science Uniersity of California, Dais Oeriew

More information

x 1 w 1 y 1 z 1 w 2 x 2 y 2 z 2 x 3 w 3 n 1 n 2 n 3 z3 y 3

x 1 w 1 y 1 z 1 w 2 x 2 y 2 z 2 x 3 w 3 n 1 n 2 n 3 z3 y 3 DIRECTED TREE NETWORKS Technological deelopments in the eld of optical communication networks using waelengthdiision multiplexing hae triggered intensie research in an optimization problem concerning the

More information

TECHNICAL RESEARCH REPORT

TECHNICAL RESEARCH REPORT TECHNICAL RESEARCH REPORT Scalable Coding of Video Objects by R. Haridasan, J. Baras CSHCN T.R. 98-1 (ISR T.R. 98-9) The Center for Satellite and Hybrid Communication Networs is a NASA-sponsored Commercial

More information

Windrose Planarity: Embedding Graphs with Direction-Constrained Edges

Windrose Planarity: Embedding Graphs with Direction-Constrained Edges Windrose Planarity: Embedding Graphs with Direction-Constrained Edges Patrizio Angelini Giordano Da Lozzo Giuseppe Di Battista Valentino Di Donato Philipp Kindermann Günter Rote Ignaz Rutter Abstract Gien

More information

Virtual Backbone Construction for Cognitive Radio Networks without Common Control Channel

Virtual Backbone Construction for Cognitive Radio Networks without Common Control Channel Virtual Backbone Construction for Cognitie Radio Networks without Common Control Channel Ying Dai, Jie Wu, and ChunSheng Xin Department of Computer and Information Sciences, Temple Uniersity, Philadelphia,

More information

Efficient Top-k Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling

Efficient Top-k Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence Efficient Top-k Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling Takuya Akiba, Takanori Hayashi, Nozomi

More information

PHOTOREALISTIC BUILDING MODELING AND VISUALIZATION IN 3-D GEOSPATIAL INFORMATION SYSTEM

PHOTOREALISTIC BUILDING MODELING AND VISUALIZATION IN 3-D GEOSPATIAL INFORMATION SYSTEM PHOTOEALISTIC BUILDING MODELING AND VISUALIZATION IN 3-D GEOSPATIAL INFOMATION SYSTEM Yonghak Song Jie Shan Geomatics Engineering, School of Ciil Engineering, Purdue Uniersity 550 Stadium Mall Drie, West

More information

Formally verifying the correctness of a network-based protocol for railway signalling systems

Formally verifying the correctness of a network-based protocol for railway signalling systems Urban Transport 197 Formally erifying the correctness of a network-based protocol for railway signalling systems J.-G. Hwang & J.-H. Lee Railway Signalling Research Group, Korea Railroad Research Institute

More information

Simulation of Large Deformations in Elastic Solids via an Eulerian Approach

Simulation of Large Deformations in Elastic Solids via an Eulerian Approach Simulation of Large Deformations in Elastic Solids ia an Eulerian Approach Shayan Hoshyari Department of Computer Science, Uniersity of British Columbia Abstract A considerable challenge in simulating

More information

An Application of Optical Flow Calculation Using Runway Image: A Preliminary Study

An Application of Optical Flow Calculation Using Runway Image: A Preliminary Study Conference on Adances in Communication and Control Systems 203 (CAC2S 203) An Application of Optical Flow Calculation Using Runway Image: A Preliminary Study Raja Munusamy Department of Aerospace Engineering,

More information

Ranking Objects by Exploiting Relationships: Computing Top-K over Aggregation

Ranking Objects by Exploiting Relationships: Computing Top-K over Aggregation Ranking Objects by Exploiting Relationships: Computing Top-K over Aggregation Kaushik Chakrabarti Venkatesh Ganti Jiawei Han Dong Xin* Microsoft Research Microsoft Research University of Illinois University

More information

Tracing Ray Differentials

Tracing Ray Differentials Tracing Ray Differentials Homan Igehy Computer Science Department Stanford Uniersity Abstract Antialiasing of ray traced images is typically performed by supersampling the image plane. While this type

More information

2 Video Quality Assessment framework for ROI-based Mobile Video Adaptation

2 Video Quality Assessment framework for ROI-based Mobile Video Adaptation 3rd International Conference on Multimedia Technology(ICMT 2013) A Noel Scheme of Video Quality Estimation for the ROI Transcoding Video Ting Yao 1. Abstract. Because of the limitation of bandwidth and

More information

Nearest neighbor classifiers

Nearest neighbor classifiers Nearest Neighbor Classification Nearest neighbor classifiers Chapter e-6 HAPT Distance based methods NN(image):. Find the image in the training data which is closest to the query image.. Return its label.

More information

UNDIRECTED GRAPHS BBM 201 DATA STRUCTURES DEPT. OF COMPUTER ENGINEERING

UNDIRECTED GRAPHS BBM 201 DATA STRUCTURES DEPT. OF COMPUTER ENGINEERING Acknowledgement: he course slides are adapted from the slides prepared by R. Sedgewick and K. Wayne of Princeton Uniersity. BBM DAA SRUCURES DEP. O COMPUER ENGINEERING UNDIRECED GRAPHS Undirected Graphs

More information

Triangulated Views Selection for Image-based Walkthrough

Triangulated Views Selection for Image-based Walkthrough Proceedings of the International MultiConference of Engineers and Computer Scientists 009 Vol I IMECS 009, March 8-0, 009, Hong Kong Triangulated Views Selection for Image-based Walkthrough Chang Ok Yun,

More information

Sub-Graph Finding Information over Nebula Networks

Sub-Graph Finding Information over Nebula Networks ISSN (e): 2250 3005 Volume, 05 Issue, 10 October 2015 International Journal of Computational Engineering Research (IJCER) Sub-Graph Finding Information over Nebula Networks K.Eswara Rao $1, A.NagaBhushana

More information

PBS: A Pseudo-Boolean Solver and Optimizer

PBS: A Pseudo-Boolean Solver and Optimizer PBS: A Pseudo-Boolean Soler and Optimizer Fadi A. Aloul, Arathi Ramani, Igor L. Marko, Karem A. Sakallah Uniersity of Michigan 2002 Fadi A. Aloul, Uniersity of Michigan Motiation SAT Solers Apps: Verification,

More information

Mining frequent Closed Graph Pattern

Mining frequent Closed Graph Pattern Mining frequent Closed Graph Pattern Seminar aus maschninellem Lernen Referent: Yingting Fan 5.November Fachbereich 21 Institut Knowledge Engineering Prof. Fürnkranz 1 Outline Motivation and introduction

More information

Reduced memory augmented Lagrangian algorithm for 3D iterative X-ray CT image reconstruction

Reduced memory augmented Lagrangian algorithm for 3D iterative X-ray CT image reconstruction Reduced memory augmented Lagrangian algorithm for 3D iteratie X-ray CT image reconstruction Madison G. McGaffin, Sathish Ramani, and Jeffrey A. Fessler Department of Electrical Engineering and Computer

More information