SPECTRAL SPARSIFICATION IN SPECTRAL CLUSTERING

Size: px
Start display at page:

Download "SPECTRAL SPARSIFICATION IN SPECTRAL CLUSTERING"

Transcription

1 SPECTRAL SPARSIFICATION IN SPECTRAL CLUSTERING Alireza Chakeri, Hamidreza Farhidzadeh, Lawrence O. Hall Department of Computer Science and Engineering College of Engineering University of South Florida

2 Clustering Problem Partition the data into groups so that points in a group are similar and points in different groups are dissimilar. Feature-based: Objects are explicitly described by their attributes. Similarity-based (Graph-based): Tuple of two objects are given a similarity value. Feature-based data can be converted into similarity-based data. Gaussian kernel similarity function, cosine distance, More general representation Applications: Bioinformatics Social networks Computer Vision * 2

3 Spectral Clustering Treats clustering as a graph partitioning problem without making specific assumptions on the form of the clusters. It works with a Laplacian matrix. Common method: k-way spectral clustering Recursively use the Eigen vector with the second smallest Eigen value (Fielder vector) to bipartition the graph into two parts. cut 3

4 Cons of Spectral Clustering Computationally expensive for large datasets. It requires significant time and memory to compute eigenvectors of the Laplacian matrix. Common approaches: make the similarity matrix sparse by zeroing out some of its elements. Then use sparse Eigensolver such as SLEPc and ARPACK This is equivalent to removing some edges of the graph. Same graph but with fewer edges 4

5 Graph Sparsification Methods Common Combinatorial Sparsifiers: ϵ-neighborhood graph K nearest neighbor graph Cut sparsifier there is no approximation guarantee on preserving the spectral properties of the original Laplacian matrix. Spectral Sparsification Based on spectral properties of graphs. Strictly stronger than cut sparsifier. Spielman and Srivastava theorem: Every graph has a spectral sparsifier preserving its spectral properties. 5

6 Spectral Sparsification Observation: Graphs with similar Laplacian matrices have similar cut values, effective resistance, and other important combinatorial properties. A sparsified graph has: Similar Laplacian matrix with its original graph. Fewer edges (number of edges can be controlled by a sampling parameter). Its edges are reweighted edges of its original set. Example: Original graph How to sparsify: Sampling by effective resistance technique Sparsifier 6

7 Partitions of Sparsifier ~ Partitions of Graph Motivation: How close are the partitions of a sparsifier to the partitions of the original graph? In other words How does the Fiedler vector of a sparsifier differs from the Fiedler vector of the original graph? Observation: any vector whose Rayleigh quotient is close to the secondsmallest eigenvalue of the Laplacian matrix can also be used to find a good partition: Theorem: we prove that Fiedler vector of a sparsifier is an approximate Fielder vector of the original graph. Partitions of sparsifier approximate partitions of graph 7

8 Cluster Structure Preservation Even for a reasonably large ε, the underlying structure of a data set is preserved by the sparsifier: the sparsifier more likely contains vertices from all of the clusters of the graph. original data ε = 2 Remove data points that are not connected to any other data points in the sparsified graph ε = 10 ε = 25 8

9 Results - compatibility with the original partitions Ground truth labels: results of applying spectral clustering on the original graph Quality comparison: rand index (RI), variation of information (VOI), global consistency error (GCE). Metric ε = 1 ε = 2 ε = 3 RI GCE VOI # of edges Jain Data set* Number of instances Number of edges = = the number of edges decreases significantly (45 times) without ruining the clusters quality. * Anil K. Jain and Martin H.C. Law, Data Clustering: A User's Dilemma 9

10 Results - comparison with k-nearest neighbor sparsifier We fix ε = 3, and find k that leads to almost the same number of edges: To see why this happens: The spectral sparsifier approximates the original Fiedler vector much better than the nearest neighbor graph. 10

11 Results - sensitivity to ε Sensitivity of spectral sparsifiers to ε k-nearest neighbor to k The Fiedler vectors of spectral sparsifiers for ε = 1, 2, 3 and k-nearest neighbor for k = 10, 20, 30 Almost same number of edges Spectral sparsifier k-nearest neighbor sparsifier 11

12 CHALLENGES AND FUTURE WORK Computing and storing the entire similarity matrix, before sparsification starts: Quadratic complexity Recently, a semi-streaming setting for the spectral sparsification which runs as quick as the Spielman-Srivastava algorithm has been developed: That is as we read edges of the graph, we add them to the sparsifier. When the sparsifier gets too big, we re-sparsify it in linear time. 12

13 Summary Graph spectral clustering algorithms suffer from time and memory complexity. We adopt spectral sparsification by sampling using effective resistance to sparsify the graph Laplacian. We showed that the Fiedler vector of the sparsified graph provides a good approximation of the Fiedler vector of the original graph even when the sampling rate is low. The partitions of the sparsifier are very similar to the partitions of the original graph even when lots of sparsification is done. 13

14 Questions? Thank you 14

Spectral Sparsification in Spectral Clustering

Spectral Sparsification in Spectral Clustering Spectral Sparsification in Spectral Clustering Alireza Chakeri, Hamidreza Farhidzadeh, Lawrence O. Hall Computer Science and Engineering Department University of South Florida Tampa, Florida Email: chakeri@mail.usf.edu,

More information

Spectral Graph Sparsification: overview of theory and practical methods. Yiannis Koutis. University of Puerto Rico - Rio Piedras

Spectral Graph Sparsification: overview of theory and practical methods. Yiannis Koutis. University of Puerto Rico - Rio Piedras Spectral Graph Sparsification: overview of theory and practical methods Yiannis Koutis University of Puerto Rico - Rio Piedras Graph Sparsification or Sketching Compute a smaller graph that preserves some

More information

Aarti Singh. Machine Learning / Slides Courtesy: Eric Xing, M. Hein & U.V. Luxburg

Aarti Singh. Machine Learning / Slides Courtesy: Eric Xing, M. Hein & U.V. Luxburg Spectral Clustering Aarti Singh Machine Learning 10-701/15-781 Apr 7, 2010 Slides Courtesy: Eric Xing, M. Hein & U.V. Luxburg 1 Data Clustering Graph Clustering Goal: Given data points X1,, Xn and similarities

More information

Spectral Clustering X I AO ZE N G + E L HA M TA BA S SI CS E CL A S S P R ESENTATION MA RCH 1 6,

Spectral Clustering X I AO ZE N G + E L HA M TA BA S SI CS E CL A S S P R ESENTATION MA RCH 1 6, Spectral Clustering XIAO ZENG + ELHAM TABASSI CSE 902 CLASS PRESENTATION MARCH 16, 2017 1 Presentation based on 1. Von Luxburg, Ulrike. "A tutorial on spectral clustering." Statistics and computing 17.4

More information

Spectral Clustering. Presented by Eldad Rubinstein Based on a Tutorial by Ulrike von Luxburg TAU Big Data Processing Seminar December 14, 2014

Spectral Clustering. Presented by Eldad Rubinstein Based on a Tutorial by Ulrike von Luxburg TAU Big Data Processing Seminar December 14, 2014 Spectral Clustering Presented by Eldad Rubinstein Based on a Tutorial by Ulrike von Luxburg TAU Big Data Processing Seminar December 14, 2014 What are we going to talk about? Introduction Clustering and

More information

Big Data Analytics. Special Topics for Computer Science CSE CSE Feb 11

Big Data Analytics. Special Topics for Computer Science CSE CSE Feb 11 Big Data Analytics Special Topics for Computer Science CSE 4095-001 CSE 5095-005 Feb 11 Fei Wang Associate Professor Department of Computer Science and Engineering fei_wang@uconn.edu Clustering II Spectral

More information

Visual Representations for Machine Learning

Visual Representations for Machine Learning Visual Representations for Machine Learning Spectral Clustering and Channel Representations Lecture 1 Spectral Clustering: introduction and confusion Michael Felsberg Klas Nordberg The Spectral Clustering

More information

CSCI-B609: A Theorist s Toolkit, Fall 2016 Sept. 6, Firstly let s consider a real world problem: community detection.

CSCI-B609: A Theorist s Toolkit, Fall 2016 Sept. 6, Firstly let s consider a real world problem: community detection. CSCI-B609: A Theorist s Toolkit, Fall 016 Sept. 6, 016 Lecture 03: The Sparsest Cut Problem and Cheeger s Inequality Lecturer: Yuan Zhou Scribe: Xuan Dong We will continue studying the spectral graph theory

More information

Introduction to spectral clustering

Introduction to spectral clustering Introduction to spectral clustering Denis Hamad LASL ULCO Denis.Hamad@lasl.univ-littoral.fr Philippe Biela HEI LAGIS Philippe.Biela@hei.fr Data Clustering Data clustering Data clustering is an important

More information

Laplacian Paradigm 2.0

Laplacian Paradigm 2.0 Laplacian Paradigm 2.0 8:40-9:10: Merging Continuous and Discrete(Richard Peng) 9:10-9:50: Beyond Laplacian Solvers (Aaron Sidford) 9:50-10:30: Approximate Gaussian Elimination (Sushant Sachdeva) 10:30-11:00:

More information

Targil 12 : Image Segmentation. Image segmentation. Why do we need it? Image segmentation

Targil 12 : Image Segmentation. Image segmentation. Why do we need it? Image segmentation Targil : Image Segmentation Image segmentation Many slides from Steve Seitz Segment region of the image which: elongs to a single object. Looks uniform (gray levels, color ) Have the same attributes (texture

More information

Community Detection. Community

Community Detection. Community Community Detection Community In social sciences: Community is formed by individuals such that those within a group interact with each other more frequently than with those outside the group a.k.a. group,

More information

Normalized Graph cuts. by Gopalkrishna Veni School of Computing University of Utah

Normalized Graph cuts. by Gopalkrishna Veni School of Computing University of Utah Normalized Graph cuts by Gopalkrishna Veni School of Computing University of Utah Image segmentation Image segmentation is a grouping technique used for image. It is a way of dividing an image into different

More information

SAMG: Sparsified Graph-Theoretic Algebraic Multigrid for Solving Large Symmetric Diagonally Dominant (SDD) Matrices

SAMG: Sparsified Graph-Theoretic Algebraic Multigrid for Solving Large Symmetric Diagonally Dominant (SDD) Matrices SAMG: Sparsified Graph-Theoretic Algebraic Multigrid for Solving Large Symmetric Diagonally Dominant (SDD) Matrices Zhiqiang Zhao Department of ECE Michigan Technological University Houghton, Michigan

More information

SDD Solvers: Bridging theory and practice

SDD Solvers: Bridging theory and practice Yiannis Koutis University of Puerto Rico, Rio Piedras joint with Gary Miller, Richard Peng Carnegie Mellon University SDD Solvers: Bridging theory and practice The problem: Solving very large Laplacian

More information

Semi-supervised Data Representation via Affinity Graph Learning

Semi-supervised Data Representation via Affinity Graph Learning 1 Semi-supervised Data Representation via Affinity Graph Learning Weiya Ren 1 1 College of Information System and Management, National University of Defense Technology, Changsha, Hunan, P.R China, 410073

More information

Machine Learning for Data Science (CS4786) Lecture 11

Machine Learning for Data Science (CS4786) Lecture 11 Machine Learning for Data Science (CS4786) Lecture 11 Spectral Clustering Course Webpage : http://www.cs.cornell.edu/courses/cs4786/2016fa/ Survey Survey Survey Competition I Out! Preliminary report of

More information

Introduction to spectral clustering

Introduction to spectral clustering Introduction to spectral clustering Vasileios Zografos zografos@isy.liu.se Klas Nordberg klas@isy.liu.se What this course is Basic introduction into the core ideas of spectral clustering Sufficient to

More information

Introduction to Machine Learning

Introduction to Machine Learning Introduction to Machine Learning Clustering Varun Chandola Computer Science & Engineering State University of New York at Buffalo Buffalo, NY, USA chandola@buffalo.edu Chandola@UB CSE 474/574 1 / 19 Outline

More information

Clustering Lecture 4: Density-based Methods

Clustering Lecture 4: Density-based Methods Clustering Lecture 4: Density-based Methods Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced

More information

Image Segmentation. Srikumar Ramalingam School of Computing University of Utah. Slides borrowed from Ross Whitaker

Image Segmentation. Srikumar Ramalingam School of Computing University of Utah. Slides borrowed from Ross Whitaker Image Segmentation Srikumar Ramalingam School of Computing University of Utah Slides borrowed from Ross Whitaker Segmentation Semantic Segmentation Indoor layout estimation What is Segmentation? Partitioning

More information

Spectral Clustering on Handwritten Digits Database

Spectral Clustering on Handwritten Digits Database October 6, 2015 Spectral Clustering on Handwritten Digits Database Danielle dmiddle1@math.umd.edu Advisor: Kasso Okoudjou kasso@umd.edu Department of Mathematics University of Maryland- College Park Advance

More information

Lecture 19: Graph Partitioning

Lecture 19: Graph Partitioning Lecture 19: Graph Partitioning David Bindel 3 Nov 2011 Logistics Please finish your project 2. Please start your project 3. Graph partitioning Given: Graph G = (V, E) Possibly weights (W V, W E ). Possibly

More information

Spectral Surface Reconstruction from Noisy Point Clouds

Spectral Surface Reconstruction from Noisy Point Clouds Spectral Surface Reconstruction from Noisy Point Clouds 1. Briefly summarize the paper s contributions. Does it address a new problem? Does it present a new approach? Does it show new types of results?

More information

Clustering With Multi-Layer Graphs: A Spectral Perspective

Clustering With Multi-Layer Graphs: A Spectral Perspective 5820 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 60, NO. 11, NOVEMBER 2012 Clustering With Multi-Layer Graphs: A Spectral Perspective Xiaowen Dong, Pascal Frossard, Senior Member, IEEE, Pierre Vandergheynst,

More information

Large-Scale Face Manifold Learning

Large-Scale Face Manifold Learning Large-Scale Face Manifold Learning Sanjiv Kumar Google Research New York, NY * Joint work with A. Talwalkar, H. Rowley and M. Mohri 1 Face Manifold Learning 50 x 50 pixel faces R 2500 50 x 50 pixel random

More information

Clustering in Networks

Clustering in Networks Clustering in Networks (Spectral Clustering with the Graph Laplacian... a brief introduction) Tom Carter Computer Science CSU Stanislaus http://csustan.csustan.edu/ tom/clustering April 1, 2012 1 Our general

More information

SGN (4 cr) Chapter 11

SGN (4 cr) Chapter 11 SGN-41006 (4 cr) Chapter 11 Clustering Jussi Tohka & Jari Niemi Department of Signal Processing Tampere University of Technology February 25, 2014 J. Tohka & J. Niemi (TUT-SGN) SGN-41006 (4 cr) Chapter

More information

Mining Social Network Graphs

Mining Social Network Graphs Mining Social Network Graphs Analysis of Large Graphs: Community Detection Rafael Ferreira da Silva rafsilva@isi.edu http://rafaelsilva.com Note to other teachers and users of these slides: We would be

More information

Kernighan/Lin - Preliminary Definitions. Comments on Kernighan/Lin Algorithm. Partitioning Without Nodal Coordinates Kernighan/Lin

Kernighan/Lin - Preliminary Definitions. Comments on Kernighan/Lin Algorithm. Partitioning Without Nodal Coordinates Kernighan/Lin Partitioning Without Nodal Coordinates Kernighan/Lin Given G = (N,E,W E ) and a partitioning N = A U B, where A = B. T = cost(a,b) = edge cut of A and B partitions. Find subsets X of A and Y of B with

More information

CS 140: Sparse Matrix-Vector Multiplication and Graph Partitioning

CS 140: Sparse Matrix-Vector Multiplication and Graph Partitioning CS 140: Sparse Matrix-Vector Multiplication and Graph Partitioning Parallel sparse matrix-vector product Lay out matrix and vectors by rows y(i) = sum(a(i,j)*x(j)) Only compute terms with A(i,j) 0 P0 P1

More information

Lecture 7: Segmentation. Thursday, Sept 20

Lecture 7: Segmentation. Thursday, Sept 20 Lecture 7: Segmentation Thursday, Sept 20 Outline Why segmentation? Gestalt properties, fun illusions and/or revealing examples Clustering Hierarchical K-means Mean Shift Graph-theoretic Normalized cuts

More information

Graphs in Machine Learning

Graphs in Machine Learning Graphs in Machine Learning Michal Valko Inria Lille - Nord Europe, France TA: Daniele Calandriello Partially based on material by: Toma s Koca k, Nikhil Srivastava, Yiannis Koutis, Joshua Batson, Daniel

More information

Clustering. SC4/SM4 Data Mining and Machine Learning, Hilary Term 2017 Dino Sejdinovic

Clustering. SC4/SM4 Data Mining and Machine Learning, Hilary Term 2017 Dino Sejdinovic Clustering SC4/SM4 Data Mining and Machine Learning, Hilary Term 2017 Dino Sejdinovic Clustering is one of the fundamental and ubiquitous tasks in exploratory data analysis a first intuition about the

More information

Behavioral Data Mining. Lecture 18 Clustering

Behavioral Data Mining. Lecture 18 Clustering Behavioral Data Mining Lecture 18 Clustering Outline Why? Cluster quality K-means Spectral clustering Generative Models Rationale Given a set {X i } for i = 1,,n, a clustering is a partition of the X i

More information

Data fusion and multi-cue data matching using diffusion maps

Data fusion and multi-cue data matching using diffusion maps Data fusion and multi-cue data matching using diffusion maps Stéphane Lafon Collaborators: Raphy Coifman, Andreas Glaser, Yosi Keller, Steven Zucker (Yale University) Part of this work was supported by

More information

A Local Learning Approach for Clustering

A Local Learning Approach for Clustering A Local Learning Approach for Clustering Mingrui Wu, Bernhard Schölkopf Max Planck Institute for Biological Cybernetics 72076 Tübingen, Germany {mingrui.wu, bernhard.schoelkopf}@tuebingen.mpg.de Abstract

More information

Homework 4: Clustering, Recommenders, Dim. Reduction, ML and Graph Mining (due November 19 th, 2014, 2:30pm, in class hard-copy please)

Homework 4: Clustering, Recommenders, Dim. Reduction, ML and Graph Mining (due November 19 th, 2014, 2:30pm, in class hard-copy please) Virginia Tech. Computer Science CS 5614 (Big) Data Management Systems Fall 2014, Prakash Homework 4: Clustering, Recommenders, Dim. Reduction, ML and Graph Mining (due November 19 th, 2014, 2:30pm, in

More information

Hypergraph Exploitation for Data Sciences

Hypergraph Exploitation for Data Sciences Photos placed in horizontal position with even amount of white space between photos and header Hypergraph Exploitation for Data Sciences Photos placed in horizontal position with even amount of white space

More information

Parallel Spectral Clustering in Distributed Systems

Parallel Spectral Clustering in Distributed Systems 1 Parallel Spectral Clustering in Distributed Systems Wen-Yen Chen, Yangqiu Song, Hongjie Bai, Chih-Jen Lin, Edward Y. Chang Abstract Spectral clustering algorithms have been shown to be more effective

More information

Social Network Analysis

Social Network Analysis Social Network Analysis Mathematics of Networks Manar Mohaisen Department of EEC Engineering Adjacency matrix Network types Edge list Adjacency list Graph representation 2 Adjacency matrix Adjacency matrix

More information

Relative Constraints as Features

Relative Constraints as Features Relative Constraints as Features Piotr Lasek 1 and Krzysztof Lasek 2 1 Chair of Computer Science, University of Rzeszow, ul. Prof. Pigonia 1, 35-510 Rzeszow, Poland, lasek@ur.edu.pl 2 Institute of Computer

More information

Lesson 2 7 Graph Partitioning

Lesson 2 7 Graph Partitioning Lesson 2 7 Graph Partitioning The Graph Partitioning Problem Look at the problem from a different angle: Let s multiply a sparse matrix A by a vector X. Recall the duality between matrices and graphs:

More information

Planar Graphs 2, the Colin de Verdière Number

Planar Graphs 2, the Colin de Verdière Number Spectral Graph Theory Lecture 26 Planar Graphs 2, the Colin de Verdière Number Daniel A. Spielman December 4, 2009 26.1 Introduction In this lecture, I will introduce the Colin de Verdière number of a

More information

Spectral Clustering and Community Detection in Labeled Graphs

Spectral Clustering and Community Detection in Labeled Graphs Spectral Clustering and Community Detection in Labeled Graphs Brandon Fain, Stavros Sintos, Nisarg Raval Machine Learning (CompSci 571D / STA 561D) December 7, 2015 {btfain, nisarg, ssintos} at cs.duke.edu

More information

CS 231A CA Session: Problem Set 4 Review. Kevin Chen May 13, 2016

CS 231A CA Session: Problem Set 4 Review. Kevin Chen May 13, 2016 CS 231A CA Session: Problem Set 4 Review Kevin Chen May 13, 2016 PS4 Outline Problem 1: Viewpoint estimation Problem 2: Segmentation Meanshift segmentation Normalized cut Problem 1: Viewpoint Estimation

More information

Applications. Foreground / background segmentation Finding skin-colored regions. Finding the moving objects. Intelligent scissors

Applications. Foreground / background segmentation Finding skin-colored regions. Finding the moving objects. Intelligent scissors Segmentation I Goal Separate image into coherent regions Berkeley segmentation database: http://www.eecs.berkeley.edu/research/projects/cs/vision/grouping/segbench/ Slide by L. Lazebnik Applications Intelligent

More information

Clustering. Informal goal. General types of clustering. Applications: Clustering in information search and analysis. Example applications in search

Clustering. Informal goal. General types of clustering. Applications: Clustering in information search and analysis. Example applications in search Informal goal Clustering Given set of objects and measure of similarity between them, group similar objects together What mean by similar? What is good grouping? Computation time / quality tradeoff 1 2

More information

Homomorphic Sketches Shrinking Big Data without Sacrificing Structure. Andrew McGregor University of Massachusetts

Homomorphic Sketches Shrinking Big Data without Sacrificing Structure. Andrew McGregor University of Massachusetts Homomorphic Sketches Shrinking Big Data without Sacrificing Structure Andrew McGregor University of Massachusetts 4Mv 2 2 32 3 2 3 2 3 4 M 5 3 5 = v 6 7 4 5 = 4Mv5 = 4Mv5 Sketches: Encode data as vector;

More information

My favorite application using eigenvalues: partitioning and community detection in social networks

My favorite application using eigenvalues: partitioning and community detection in social networks My favorite application using eigenvalues: partitioning and community detection in social networks Will Hobbs February 17, 2013 Abstract Social networks are often organized into families, friendship groups,

More information

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervised Learning and Clustering Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2009 CS 551, Spring 2009 c 2009, Selim Aksoy (Bilkent University)

More information

Lecture 25: Element-wise Sampling of Graphs and Linear Equation Solving, Cont. 25 Element-wise Sampling of Graphs and Linear Equation Solving,

Lecture 25: Element-wise Sampling of Graphs and Linear Equation Solving, Cont. 25 Element-wise Sampling of Graphs and Linear Equation Solving, Stat260/CS294: Randomized Algorithms for Matrices and Data Lecture 25-12/04/2013 Lecture 25: Element-wise Sampling of Graphs and Linear Equation Solving, Cont. Lecturer: Michael Mahoney Scribe: Michael

More information

Anomaly Detection on Data Streams with High Dimensional Data Environment

Anomaly Detection on Data Streams with High Dimensional Data Environment Anomaly Detection on Data Streams with High Dimensional Data Environment Mr. D. Gokul Prasath 1, Dr. R. Sivaraj, M.E, Ph.D., 2 Department of CSE, Velalar College of Engineering & Technology, Erode 1 Assistant

More information

Vertex Weighted Feature Engineering in Machine Learning

Vertex Weighted Feature Engineering in Machine Learning Vertex Weighted Feature Engineering in Machine Learning Jeff and Debra Knisley Monday, October 17, 216 Coming up with features is difficult, timeconsuming, requires expert knowledge. Applied machine learning

More information

Partitioning and Partitioning Tools. Tim Barth NASA Ames Research Center Moffett Field, California USA

Partitioning and Partitioning Tools. Tim Barth NASA Ames Research Center Moffett Field, California USA Partitioning and Partitioning Tools Tim Barth NASA Ames Research Center Moffett Field, California 94035-00 USA 1 Graph/Mesh Partitioning Why do it? The graph bisection problem What are the standard heuristic

More information

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering May 12 2017 2 Content 1. Introduction 2. Proposed Technique 2.1 Learning Fast Localized Spectral Filters 2.2 Graph Coarsening

More information

Hierarchical Multi level Approach to graph clustering

Hierarchical Multi level Approach to graph clustering Hierarchical Multi level Approach to graph clustering by: Neda Shahidi neda@cs.utexas.edu Cesar mantilla, cesar.mantilla@mail.utexas.edu Advisor: Dr. Inderjit Dhillon Introduction Data sets can be presented

More information

Social-Network Graphs

Social-Network Graphs Social-Network Graphs Mining Social Networks Facebook, Google+, Twitter Email Networks, Collaboration Networks Identify communities Similar to clustering Communities usually overlap Identify similarities

More information

Scalable Clustering of Signed Networks Using Balance Normalized Cut

Scalable Clustering of Signed Networks Using Balance Normalized Cut Scalable Clustering of Signed Networks Using Balance Normalized Cut Kai-Yang Chiang,, Inderjit S. Dhillon The 21st ACM International Conference on Information and Knowledge Management (CIKM 2012) Oct.

More information

Data Preprocessing. Javier Béjar. URL - Spring 2018 CS - MAI 1/78 BY: $\

Data Preprocessing. Javier Béjar. URL - Spring 2018 CS - MAI 1/78 BY: $\ Data Preprocessing Javier Béjar BY: $\ URL - Spring 2018 C CS - MAI 1/78 Introduction Data representation Unstructured datasets: Examples described by a flat set of attributes: attribute-value matrix Structured

More information

Cluster Analysis (b) Lijun Zhang

Cluster Analysis (b) Lijun Zhang Cluster Analysis (b) Lijun Zhang zlj@nju.edu.cn http://cs.nju.edu.cn/zlj Outline Grid-Based and Density-Based Algorithms Graph-Based Algorithms Non-negative Matrix Factorization Cluster Validation Summary

More information

MultiDimensional Signal Processing Master Degree in Ingegneria delle Telecomunicazioni A.A

MultiDimensional Signal Processing Master Degree in Ingegneria delle Telecomunicazioni A.A MultiDimensional Signal Processing Master Degree in Ingegneria delle Telecomunicazioni A.A. 205-206 Pietro Guccione, PhD DEI - DIPARTIMENTO DI INGEGNERIA ELETTRICA E DELL INFORMAZIONE POLITECNICO DI BARI

More information

Parallel Rendering. Jongwook Jin Kwangyun Wohn VR Lab. CS Dept. KAIST MAR

Parallel Rendering. Jongwook Jin Kwangyun Wohn VR Lab. CS Dept. KAIST MAR Optimal Partition for Parallel Rendering Jongwook Jin Kwangyun Wohn VR Lab. CS Dept. KAIST Culture Technology Research Center MAR.06.2008 Optimal Partition for Parallel Rendering Load balanced partition

More information

Clustering will not be satisfactory if:

Clustering will not be satisfactory if: Clustering will not be satisfactory if: -- in the input space the clusters are not linearly separable; -- the distance measure is not adequate; -- the assumptions limit the shape or the number of the clusters.

More information

( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components

( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components Review Lecture 14 ! PRINCIPAL COMPONENT ANALYSIS Eigenvectors of the covariance matrix are the principal components 1. =cov X Top K principal components are the eigenvectors with K largest eigenvalues

More information

Fast Nearest Neighbor Search on Large Time-Evolving Graphs

Fast Nearest Neighbor Search on Large Time-Evolving Graphs Fast Nearest Neighbor Search on Large Time-Evolving Graphs Leman Akoglu Srinivasan Parthasarathy Rohit Khandekar Vibhore Kumar Deepak Rajan Kun-Lung Wu Graphs are everywhere Leman Akoglu Fast Nearest Neighbor

More information

Graph Partitioning for High-Performance Scientific Simulations. Advanced Topics Spring 2008 Prof. Robert van Engelen

Graph Partitioning for High-Performance Scientific Simulations. Advanced Topics Spring 2008 Prof. Robert van Engelen Graph Partitioning for High-Performance Scientific Simulations Advanced Topics Spring 2008 Prof. Robert van Engelen Overview Challenges for irregular meshes Modeling mesh-based computations as graphs Static

More information

Discriminative Clustering for Image Co-Segmentation

Discriminative Clustering for Image Co-Segmentation Discriminative Clustering for Image Co-Segmentation Joulin, A.; Bach, F.; Ponce, J. (CVPR. 2010) Iretiayo Akinola Josh Tennefoss Outline Why Co-segmentation? Previous Work Problem Formulation Experimental

More information

The goals of segmentation

The goals of segmentation Image segmentation The goals of segmentation Group together similar-looking pixels for efficiency of further processing Bottom-up process Unsupervised superpixels X. Ren and J. Malik. Learning a classification

More information

Hashing with Graphs. Sanjiv Kumar (Google), and Shih Fu Chang (Columbia) June, 2011

Hashing with Graphs. Sanjiv Kumar (Google), and Shih Fu Chang (Columbia) June, 2011 Hashing with Graphs Wei Liu (Columbia Columbia), Jun Wang (IBM IBM), Sanjiv Kumar (Google), and Shih Fu Chang (Columbia) June, 2011 Overview Graph Hashing Outline Anchor Graph Hashing Experiments Conclusions

More information

Graph Approximation and Clustering on a Budget

Graph Approximation and Clustering on a Budget Graph Approximation and Clustering on a Budget Ethan Fetaya Ohad Shamir Shimon Ullman Weizmann Institute of Science Weizmann Institute of Science Weizmann Institute of Science Abstract We consider the

More information

CS 664 Slides #11 Image Segmentation. Prof. Dan Huttenlocher Fall 2003

CS 664 Slides #11 Image Segmentation. Prof. Dan Huttenlocher Fall 2003 CS 664 Slides #11 Image Segmentation Prof. Dan Huttenlocher Fall 2003 Image Segmentation Find regions of image that are coherent Dual of edge detection Regions vs. boundaries Related to clustering problems

More information

University of Florida CISE department Gator Engineering. Clustering Part 4

University of Florida CISE department Gator Engineering. Clustering Part 4 Clustering Part 4 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville DBSCAN DBSCAN is a density based clustering algorithm Density = number of

More information

Spectral Graph Multisection Through Orthogonality. Huanyang Zheng and Jie Wu CIS Department, Temple University

Spectral Graph Multisection Through Orthogonality. Huanyang Zheng and Jie Wu CIS Department, Temple University Spectral Graph Multisection Through Orthogonality Huanyang Zheng and Jie Wu CIS Department, Temple University Outline Motivation Preliminary Algorithm Evaluation Future work Motivation Traditional graph

More information

Nonparametric Importance Sampling for Big Data

Nonparametric Importance Sampling for Big Data Nonparametric Importance Sampling for Big Data Abigael C. Nachtsheim Research Training Group Spring 2018 Advisor: Dr. Stufken SCHOOL OF MATHEMATICAL AND STATISTICAL SCIENCES Motivation Goal: build a model

More information

Lecture 6: Unsupervised Machine Learning Dagmar Gromann International Center For Computational Logic

Lecture 6: Unsupervised Machine Learning Dagmar Gromann International Center For Computational Logic SEMANTIC COMPUTING Lecture 6: Unsupervised Machine Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 23 November 2018 Overview Unsupervised Machine Learning overview Association

More information

Clustering. So far in the course. Clustering. Clustering. Subhransu Maji. CMPSCI 689: Machine Learning. dist(x, y) = x y 2 2

Clustering. So far in the course. Clustering. Clustering. Subhransu Maji. CMPSCI 689: Machine Learning. dist(x, y) = x y 2 2 So far in the course Clustering Subhransu Maji : Machine Learning 2 April 2015 7 April 2015 Supervised learning: learning with a teacher You had training data which was (feature, label) pairs and the goal

More information

L1-graph based community detection in online social networks

L1-graph based community detection in online social networks L1-graph based community detection in online social networks Liang Huang 1, Ruixuan Li 1, Kunmei Wen 1, Xiwu Gu 1, Yuhua Li 1 and Zhiyong Xu 2 1 Huazhong University of Science and Technology 2 Suffork

More information

Lecture 11: Clustering and the Spectral Partitioning Algorithm A note on randomized algorithm, Unbiased estimates

Lecture 11: Clustering and the Spectral Partitioning Algorithm A note on randomized algorithm, Unbiased estimates CSE 51: Design and Analysis of Algorithms I Spring 016 Lecture 11: Clustering and the Spectral Partitioning Algorithm Lecturer: Shayan Oveis Gharan May nd Scribe: Yueqi Sheng Disclaimer: These notes have

More information

Fast Indexing and Search. Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation

Fast Indexing and Search. Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation Fast Indexing and Search Lida Huang, Ph.D. Senior Member of Consulting Staff Magma Design Automation Motivation Object categorization? http://www.cs.utexas.edu/~grauman/slides/jain_et_al_cvpr2008.ppt Motivation

More information

Lecture 10 CNNs on Graphs

Lecture 10 CNNs on Graphs Lecture 10 CNNs on Graphs CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 26, 2017 Two Scenarios For CNNs on graphs, we have two distinct scenarios: Scenario 1: Each

More information

Graph drawing in spectral layout

Graph drawing in spectral layout Graph drawing in spectral layout Maureen Gallagher Colleen Tygh John Urschel Ludmil Zikatanov Beginning: July 8, 203; Today is: October 2, 203 Introduction Our research focuses on the use of spectral graph

More information

Image Segmentation. Ross Whitaker SCI Institute, School of Computing University of Utah

Image Segmentation. Ross Whitaker SCI Institute, School of Computing University of Utah Image Segmentation Ross Whitaker SCI Institute, School of Computing University of Utah What is Segmentation? Partitioning images/volumes into meaningful pieces Partitioning problem Labels Isolating a specific

More information

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervised Learning and Clustering Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2008 CS 551, Spring 2008 c 2008, Selim Aksoy (Bilkent University)

More information

Clustering Part 4 DBSCAN

Clustering Part 4 DBSCAN Clustering Part 4 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville DBSCAN DBSCAN is a density based clustering algorithm Density = number of

More information

Spectral Compression of Mesh Geometry

Spectral Compression of Mesh Geometry Spectral Compression of Mesh Geometry Zachi Karni, Craig Gotsman SIGGRAPH 2000 1 Introduction Thus far, topology coding drove geometry coding. Geometric data contains far more information (15 vs. 3 bits/vertex).

More information

Lecture 9. Semidefinite programming is linear programming where variables are entries in a positive semidefinite matrix.

Lecture 9. Semidefinite programming is linear programming where variables are entries in a positive semidefinite matrix. CSE525: Randomized Algorithms and Probabilistic Analysis Lecture 9 Lecturer: Anna Karlin Scribe: Sonya Alexandrova and Keith Jia 1 Introduction to semidefinite programming Semidefinite programming is linear

More information

Extracting Information from Complex Networks

Extracting Information from Complex Networks Extracting Information from Complex Networks 1 Complex Networks Networks that arise from modeling complex systems: relationships Social networks Biological networks Distinguish from random networks uniform

More information

Machine Learning for Signal Processing Clustering. Bhiksha Raj Class Oct 2016

Machine Learning for Signal Processing Clustering. Bhiksha Raj Class Oct 2016 Machine Learning for Signal Processing Clustering Bhiksha Raj Class 11. 13 Oct 2016 1 Statistical Modelling and Latent Structure Much of statistical modelling attempts to identify latent structure in the

More information

CS 534: Computer Vision Segmentation and Perceptual Grouping

CS 534: Computer Vision Segmentation and Perceptual Grouping CS 534: Computer Vision Segmentation and Perceptual Grouping Ahmed Elgammal Dept of Computer Science CS 534 Segmentation - 1 Outlines Mid-level vision What is segmentation Perceptual Grouping Segmentation

More information

Emotion Classification

Emotion Classification Emotion Classification Shai Savir 038052395 Gil Sadeh 026511469 1. Abstract Automated facial expression recognition has received increased attention over the past two decades. Facial expressions convey

More information

Dimension Reduction CS534

Dimension Reduction CS534 Dimension Reduction CS534 Why dimension reduction? High dimensionality large number of features E.g., documents represented by thousands of words, millions of bigrams Images represented by thousands of

More information

Parallel Graph Algorithms. Richard Peng Georgia Tech

Parallel Graph Algorithms. Richard Peng Georgia Tech Parallel Graph Algorithms Richard Peng Georgia Tech OUTLINE Model and problems Graph decompositions Randomized clusterings Interface with optimization THE MODEL The `scale up approach: Have a number of

More information

FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS

FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS Jaya Susan Edith. S 1 and A.Usha Ruby 2 1 Department of Computer Science and Engineering,CSI College of Engineering, 2 Research

More information

Document Clustering Using Locality Preserving Indexing

Document Clustering Using Locality Preserving Indexing Document Clustering Using Locality Preserving Indexing Deng Cai Department of Computer Science University of Illinois at Urbana Champaign 1334 Siebel Center, 201 N. Goodwin Ave, Urbana, IL 61801, USA Phone:

More information

Clustering. Subhransu Maji. CMPSCI 689: Machine Learning. 2 April April 2015

Clustering. Subhransu Maji. CMPSCI 689: Machine Learning. 2 April April 2015 Clustering Subhransu Maji CMPSCI 689: Machine Learning 2 April 2015 7 April 2015 So far in the course Supervised learning: learning with a teacher You had training data which was (feature, label) pairs

More information

Streaming Algorithms for Matching Size in Sparse Graphs

Streaming Algorithms for Matching Size in Sparse Graphs Streaming Algorithms for Matching Size in Sparse Graphs Graham Cormode g.cormode@warwick.ac.uk Joint work with S. Muthukrishnan (Rutgers), Morteza Monemizadeh (Rutgers Amazon) Hossein Jowhari (Warwick

More information

Patterns and Computer Vision

Patterns and Computer Vision Patterns and Computer Vision Michael Anderson, Bryan Catanzaro, Jike Chong, Katya Gonina, Kurt Keutzer, Tim Mattson, Mark Murphy, David Sheffield, Bor-Yiing Su, Narayanan Sundaram and the rest of the PALLAS

More information

Spectral Clustering and Semi-Supervised learning using Evolving Similarity Graphs

Spectral Clustering and Semi-Supervised learning using Evolving Similarity Graphs Spectral Clustering and Semi-Supervised learning using Evolving Similarity Graphs Christina Chrysouli a,, Anastasios Tefas a a Department of Informatics, Aristotle University of Thessaloniki, University

More information

Convex Relaxations for Permutation Problems

Convex Relaxations for Permutation Problems Convex Relaxations for Permutation Problems Inria Junior Seminar Fajwel Fogel February 13, 2014 SIERRA team My advisors: Alexandre d Aspremont and Francis Bach Convex optimization in 7 slides Application

More information