Lifted and Constrained Sampling of Attributed Graphs with Generative Network Models

Size: px
Start display at page:

Download "Lifted and Constrained Sampling of Attributed Graphs with Generative Network Models"

Transcription

1 Lifted and Constrained Sampling of Attributed Graphs with Generative Network Models Jennifer Neville Departments of Computer Science and Statistics Purdue University (joint work with Pablo Robles Granda, and Sebastian Moreno)

2 Statistical network methods/models are critical for: Hypothesis testing Simulation of system behavior over time Understanding key system properties and causal effects

3 Many of the current generative network models are edge-based

4 Edge-based generative network models (GNMs) P A G =(V, E) Models differ wrt to how they produce edge probabilities in (e.g., ER, SBM, CL, KPGM) P

5 These models represent/learn probability distributions over the graph space Likely networks Unlikely networks P K o (G) P K o (G) G K o

6 Example: mixed Kronecker Product Graph Models

7 mixed KPGM (Moreno et al. KDD 13) Starting from an initiator matrix of b x b Bernoulli parameters ` Matrix of size b is constructed using Kronecker multiplication ` Example: apple = K =6; ` =4 Then the Bernoulli trials for the subsequent K- ` kronecker multiplications are tied Result: each edge occurs with same expectation as KPGM, but overall variance increases

8 mixed KPGM (Moreno et al. KDD 13) Starting from an initiator matrix of b x b Bernoulli parameters K =6; ` =4 ` Matrix of size b is constructed using Kronecker multiplication ` Example: apple = Then the Bernoulli trials for the subsequent K- ` kronecker multiplications are tied Result: each edge occurs with same expectation as KPGM, but overall variance increases

9 mixed KPGM (Moreno et al. KDD 13) Starting from an initiator matrix of b x b Bernoulli parameters K =6; ` =4 ` Matrix of size b is constructed using Kronecker multiplication Hierarchical structure, with tied parameters, allows mkpgm to better capture complex properties (e.g., clustering and variability) observed in real networks ` Example: apple = Other hierarchical GNMs: BTER (Seshadhri et al., 2012), bisbm (Larremore et al., 2014), nestedsbm (Peixoto, 2014) Then the Bernoulli trials for the subsequent K- ` kronecker multiplications are tied Result: each edge occurs with same expectation as KPGM, but overall variance increases

10 GNMs are typically defined procedurally (e.g., through a prescribed sampling process), which makes it difficult to compare model properties* * See the following for a nice overview: A. Jacobs, A. Clauset (2014). A unified view of generative models for networks: models, methods, opportunities, and challenges. In NIPS 2014 Workshop on Networks: From Graphs to Rich Data.

11 Observation: mkpgm can be represented as a Bayesian network V [0] P [0] Z [0] V [0] V [0] P [1] Z [1] Blocks V [0] P A Edges V [0]

12 Observation: mkpgm can be represented as a Bayesian network V [0] P [0] Z [0] V [0] V [0] P [1] Z [1] Blocks V [0] [0] P A Edges V [0] V V [0] [0] The final BN N consists of all the RVs Z [0],Z [1],,Z [ =K `] and their associated probabilities.

13 Observation: mkpgm can be represented as a Bayesian network V [0] Super-block level =0 Z [0] i V [0] Block level =1 Z [1] j A uv Edge level = V [0] - + The final BN N consists of all the RVs Z [0],Z [1],,Z [ =K `] and their associated probabilities.

14 What is the advantage of representing hierarchical GNMs as Bayesian networks?

15 Utility of BN representation for GNMs (Robles et al. IJCAI 17) Facilitates comparison between hierarchical GNM models mkpgm Sampling(, K, `){ Compute P [0] = [1] Zj Sample G[0] Bernoulli(P) For l = 1... K `: Set P [l] = G[l Enables development of generalized sampling algorithms that are provably correct and efficient [0] Zi ` 1 [2] Zk 1] A[3] uv Sample G[l] Bernoulli(P [l] ) Return graph G[l] Difficult to Compare Comparison Feasible } [0] Zi BTER Sampling( ){ Preprocess:create node groups [1] Zj Link within-block nodes with ER model Can easily identify parametric symmetries that enable lifted inference Link between-block nodes with CL model A[3] uv Return graph } Context-specific dependence sparsifies the set of RVs to be sampled. [1] Zj [0] Zi [1] Zj =0 Block level =1 Edge level =2 Auv Fig. 1 b Auv Symmetries [0] Zi Super-block level P (0) P (1) pa = P (0) P (1) pa = P (0) P (1) pa = pa = pa = [1] Zj [0] Zi [1] Zj uv BN form of Fig. 1 b Z=1 Z=0 Sparsification pa = 1 1 U [2] U [2] Fill (color/blend): represent A (latent) random variables (RVs) with the same value Arrows: represent dependencies among (RVs). Tables: Represent CPD of the RVs. Identifying symmetries is not a trivial task as described [0] Zi Auv Squares: represent binary random variables for blocks and graph links; red (sampled Z=1), grey (sampled Z=0), crosshatch indicates Z=0 (sampling prevented) due to context-specific dependence on parent rv value. Arrows: represent dependencies among rv's due to block membership.

16 Sampling algorithm for GNM transformed to BN (Robles et al. IJCAI 17) Average-case complexity: O( E )

17 So given that we have models that can efficiently generate networks with varying structure How can we extend these to generate networks with correlated attributes?

18 P G G

19 P (X, G) P E (X, E E, X )=P E (E E )P (X X ) Pr How to learn and effectively sample from P (X,G)? Discrete space with O(2 V 2 +V p ) structures X G

20 There has been work on learning joint network models e.g., PRMs (Getoor et al. 03), ERGMs (Wasserman & Patterson 96), MAGs (Kim & Leskovec 12) But since these were developed as descriptive models, it is difficult to use them to efficiently generate networks with varying structure

21 Issues with learning/sampling from full joint Learning: A single network does not provide enough data to easily learn a full joint model Pr Solution: use marginals and combine them together to approximate sampling from full joint distribution Sampling: X G Hierarchical network models concentrate mass to smaller regions to capture edge dependence this makes it difficult to identify likely networks in the sampling space Solution: develop approach that can avoid the sparse regions to produce reasonable samples from the joint distribution efficiently Likely graph structures Likely attributed graphs Space of attributed graphs

22 Sampling attributed networks: Sample attribute values for nodes; use graph model to propose edges; then sample edges conditioned on node attributes

23 G Generative Network Model P (X, G G, X ) Marginals X attributes attribute vector x Output sampled network

24 Constrained sampling of attributed graphs (CSAG) (Robles et al. KDD 16) 1.Sample attributes from P(X) 2.Sample from the [hierarchical] model P(G) 3.Sample edges by constraining G X 4.If attribute-relations are capture accurately done 5.Else go to 2, back up a level in hierarchy to further constrain sampling at that level

25 Constrained sampling of attributed graphs (CSAG) (Robles et al. KDD 16) We developed a two-stage constrained sampling process using the BN view of mkpgms G 0 Basic sampling LP sampling G K-l-2 G K-l-2 G K-l-2 Super-block level =0 Z [0] i Basic sampling LP sampling LP sampling Block level =1 Edge level = Z [1] j + - CSAG constraints bias the search to regions of the space with higher likelihood networks Auv G K-l-1 ME sampling G K-l If ρ OUT ~ ρ IN return G K-l else G K-l-1 G Replace basic K-l-1 sampling at edge else level else ME sampling with maximum ME sampling entropy (ME) constraints to sample edges that match G K-l target Gattribute K-l correlation If If ρ OUT correlation ~ ρ IN If ρ OUT ( ) ~ ρ IN not possible: back-up a level in hierarchy and return return use linear programming (LP) to G K-l G constrain block K-l sampling to facilitate better match on attribute correlation

26 CSAG results: network structure CSAG produces network structure that closely matches that of underlying mkpgm marginal

27 CSAG results: attribute correlation CSAG produces attribute correlations that closely match that of input data

28 CSAG results: overall + CSAG achieves lowest joint error + +

29 Why does it work? Computational insight: Representation and objective functions that are easy to specify (e.g. full joint, edge-based likelihood) do not always match well to goals of network learning Potential solution: Using constraints on model space and/or objectives adds inductive bias (can be easier to identify/guide towards properties of interest than to construct better representations/objective functions) Current work: Use CSAG generation method to study the transferability of relational models learned from one (sub) network to another (sub) network based on network structure and attribute correlation

30 Regularization vs. probabilistic modeling (Zeno & Neville, MLG 16) Simulation experiments based on semi-synthetic data generated from CSAG (with parameters learned from real social network data) Weighted vote relational neighbor Relational Bayes collective classifier Attribute correlation AUC Network density Network density

31 Questions?

Supporting Statistical Hypothesis Testing Over Graphs

Supporting Statistical Hypothesis Testing Over Graphs Supporting Statistical Hypothesis Testing Over Graphs Jennifer Neville Departments of Computer Science and Statistics Purdue University (joint work with Tina Eliassi-Rad, Brian Gallagher, Sergey Kirshner,

More information

Using Bayesian Network Representations for Effective Sampling from Generative Network Models

Using Bayesian Network Representations for Effective Sampling from Generative Network Models Using Bayesian Network Representations for Effective Sampling from Generative Network Models Pablo Robles-Granda and Sebastian Moreno and Jennifer Neville Computer Science Department Purdue University

More information

Using Bayesian Network Representations for Effective Sampling from Generative Network Models

Using Bayesian Network Representations for Effective Sampling from Generative Network Models Using Bayesian Network Representations for Effective Sampling from Generative Network Models Pablo Robles-Granda and Sebastian Moreno and Jennifer Neville Computer Science Department Purdue University

More information

Sampling of Attributed Networks from Hierarchical Generative Models

Sampling of Attributed Networks from Hierarchical Generative Models Sampling of Attributed Networks from Hierarchical Generative Models Pablo Robles Purdue University West Lafayette, IN USA problesg@purdue.edu Sebastian Moreno Universidad Adolfo Ibañez Viña del Mar, Chile

More information

Semi-supervised learning for node classification in networks

Semi-supervised learning for node classification in networks Semi-supervised learning for node classification in networks Jennifer Neville Departments of Computer Science and Statistics Purdue University (joint work with Paul Bennett, John Moore, and Joel Pfeiffer)

More information

How to exploit network properties to improve learning in relational domains

How to exploit network properties to improve learning in relational domains How to exploit network properties to improve learning in relational domains Jennifer Neville Departments of Computer Science and Statistics Purdue University!!!! (joint work with Brian Gallagher, Timothy

More information

Tied Kronecker Product Graph Models to Capture Variance in Network Populations

Tied Kronecker Product Graph Models to Capture Variance in Network Populations Tied Kronecker Product Graph Models to Capture Variance in Network Populations Sebastian Moreno, Sergey Kirshner +, Jennifer Neville +, SVN Vishwanathan + Department of Computer Science, + Department of

More information

Scalable and exact sampling method for probabilistic generative graph models

Scalable and exact sampling method for probabilistic generative graph models Data Min Knowl Disc https://doi.org/10.1007/s10618-018-0566-x Scalable and exact sampling method for probabilistic generative graph models Sebastian Moreno 1 Joseph J. Pfeiffer III 2 Jennifer Neville 3

More information

Computational Genomics. Systems biology. Putting it together: Data integration using graphical models

Computational Genomics. Systems biology. Putting it together: Data integration using graphical models 02-710 Computational Genomics Systems biology Putting it together: Data integration using graphical models High throughput data So far in this class we discussed several different types of high throughput

More information

Undirected Graphical Models

Undirected Graphical Models Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Properties Properties 3 Generative vs. Conditional

More information

Quilting Stochastic Kronecker Product Graphs to Generate Multiplicative Attribute Graphs

Quilting Stochastic Kronecker Product Graphs to Generate Multiplicative Attribute Graphs Quilting Stochastic Kronecker Product Graphs to Generate Multiplicative Attribute Graphs Hyokun Yun Department of Statistics Purdue University SV N Vishwanathan Departments of Statistics and Computer Science

More information

Collective classification in large scale networks. Jennifer Neville Departments of Computer Science and Statistics Purdue University

Collective classification in large scale networks. Jennifer Neville Departments of Computer Science and Statistics Purdue University Collective classification in large scale networks Jennifer Neville Departments of Computer Science and Statistics Purdue University The data mining process Network Datadata Knowledge Selection Interpretation

More information

10-810: Advanced Algorithms and Models for Computational Biology. Optimal leaf ordering and classification

10-810: Advanced Algorithms and Models for Computational Biology. Optimal leaf ordering and classification 10-810: Advanced Algorithms and Models for Computational Biology Optimal leaf ordering and classification Hierarchical clustering As we mentioned, its one of the most popular methods for clustering gene

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 3 Linear

More information

Chris Bishop s PRML Ch. 8: Graphical Models

Chris Bishop s PRML Ch. 8: Graphical Models Chris Bishop s PRML Ch. 8: Graphical Models January 24, 2008 Introduction Visualize the structure of a probabilistic model Design and motivate new models Insights into the model s properties, in particular

More information

A graph contains a set of nodes (vertices) connected by links (edges or arcs)

A graph contains a set of nodes (vertices) connected by links (edges or arcs) BOLTZMANN MACHINES Generative Models Graphical Models A graph contains a set of nodes (vertices) connected by links (edges or arcs) In a probabilistic graphical model, each node represents a random variable,

More information

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan Link Prediction Eman Badr Mohammed Saquib Akmal Khan 11-06-2013 Link Prediction Which pair of nodes should be connected? Applications Facebook friend suggestion Recommendation systems Monitoring and controlling

More information

Introduction to Probabilistic Machine Learning

Introduction to Probabilistic Machine Learning Introduction to Probabilistic Machine Learning Piyush Rai Dept. of CSE, IIT Kanpur (Mini-course 1) Nov 03, 2015 Piyush Rai (IIT Kanpur) Introduction to Probabilistic Machine Learning 1 Machine Learning

More information

K. Nishijima. Definition and use of Bayesian probabilistic networks 1/32

K. Nishijima. Definition and use of Bayesian probabilistic networks 1/32 The Probabilistic Analysis of Systems in Engineering 1/32 Bayesian probabilistic bili networks Definition and use of Bayesian probabilistic networks K. Nishijima nishijima@ibk.baug.ethz.ch 2/32 Today s

More information

Mixed Membership Stochastic Blockmodels

Mixed Membership Stochastic Blockmodels Mixed Membership Stochastic Blockmodels (2008) Edoardo M. Airoldi, David M. Blei, Stephen E. Fienberg and Eric P. Xing Herrissa Lamothe Princeton University Herrissa Lamothe (Princeton University) Mixed

More information

Overlapping Communities

Overlapping Communities Overlapping Communities Davide Mottin HassoPlattner Institute Graph Mining course Winter Semester 2017 Acknowledgements Most of this lecture is taken from: http://web.stanford.edu/class/cs224w/slides GRAPH

More information

A Shrinkage Approach for Modeling Non-Stationary Relational Autocorrelation

A Shrinkage Approach for Modeling Non-Stationary Relational Autocorrelation A Shrinkage Approach for Modeling Non-Stationary Relational Autocorrelation Pelin Angin Department of Computer Science Purdue University pangin@cs.purdue.edu Jennifer Neville Department of Computer Science

More information

2 : Directed GMs: Bayesian Networks

2 : Directed GMs: Bayesian Networks 10-708: Probabilistic Graphical Models 10-708, Spring 2017 2 : Directed GMs: Bayesian Networks Lecturer: Eric P. Xing Scribes: Jayanth Koushik, Hiroaki Hayashi, Christian Perez Topic: Directed GMs 1 Types

More information

Undirected graphical models

Undirected graphical models Undirected graphical models Semantics of probabilistic models over undirected graphs Parameters of undirected models Example applications COMP-652 and ECSE-608, February 16, 2017 1 Undirected graphical

More information

Rapid Introduction to Machine Learning/ Deep Learning

Rapid Introduction to Machine Learning/ Deep Learning Rapid Introduction to Machine Learning/ Deep Learning Hyeong In Choi Seoul National University 1/32 Lecture 5a Bayesian network April 14, 2016 2/32 Table of contents 1 1. Objectives of Lecture 5a 2 2.Bayesian

More information

Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach

Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach Author: Jaewon Yang, Jure Leskovec 1 1 Venue: WSDM 2013 Presenter: Yupeng Gu 1 Stanford University 1 Background Community

More information

Directed Graphical Models or Bayesian Networks

Directed Graphical Models or Bayesian Networks Directed Graphical Models or Bayesian Networks Le Song Machine Learning II: Advanced Topics CSE 8803ML, Spring 2012 Bayesian Networks One of the most exciting recent advancements in statistical AI Compact

More information

Bayesian Networks Basic and simple graphs

Bayesian Networks Basic and simple graphs Bayesian Networks Basic and simple graphs Ullrika Sahlin, Centre of Environmental and Climate Research Lund University, Sweden Ullrika.Sahlin@cec.lu.se http://www.cec.lu.se/ullrika-sahlin Bayesian [Belief]

More information

Naïve Bayes classification

Naïve Bayes classification Naïve Bayes classification 1 Probability theory Random variable: a variable whose possible values are numerical outcomes of a random phenomenon. Examples: A person s height, the outcome of a coin toss

More information

The connection of dropout and Bayesian statistics

The connection of dropout and Bayesian statistics The connection of dropout and Bayesian statistics Interpretation of dropout as approximate Bayesian modelling of NN http://mlg.eng.cam.ac.uk/yarin/thesis/thesis.pdf Dropout Geoffrey Hinton Google, University

More information

6.047 / Computational Biology: Genomes, Networks, Evolution Fall 2008

6.047 / Computational Biology: Genomes, Networks, Evolution Fall 2008 MIT OpenCourseWare http://ocw.mit.edu 6.047 / 6.878 Computational Biology: Genomes, Networks, Evolution Fall 2008 For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.

More information

Bayesian Learning in Undirected Graphical Models

Bayesian Learning in Undirected Graphical Models Bayesian Learning in Undirected Graphical Models Zoubin Ghahramani Gatsby Computational Neuroscience Unit University College London, UK http://www.gatsby.ucl.ac.uk/ and Center for Automated Learning and

More information

Quilting Stochastic Kronecker Graphs to Generate Multiplicative Attribute Graphs

Quilting Stochastic Kronecker Graphs to Generate Multiplicative Attribute Graphs Quilting Stochastic Kronecker Graphs to Generate Multiplicative Attribute Graphs Hyokun Yun (work with S.V.N. Vishwanathan) Department of Statistics Purdue Machine Learning Seminar November 9, 2011 Overview

More information

Nonparametric Bayesian Matrix Factorization for Assortative Networks

Nonparametric Bayesian Matrix Factorization for Assortative Networks Nonparametric Bayesian Matrix Factorization for Assortative Networks Mingyuan Zhou IROM Department, McCombs School of Business Department of Statistics and Data Sciences The University of Texas at Austin

More information

Lecture 4 October 18th

Lecture 4 October 18th Directed and undirected graphical models Fall 2017 Lecture 4 October 18th Lecturer: Guillaume Obozinski Scribe: In this lecture, we will assume that all random variables are discrete, to keep notations

More information

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Some slides are due to Christopher Bishop Limitations of K-means Hard assignments of data points to clusters small shift of a

More information

Graphical Models and Kernel Methods

Graphical Models and Kernel Methods Graphical Models and Kernel Methods Jerry Zhu Department of Computer Sciences University of Wisconsin Madison, USA MLSS June 17, 2014 1 / 123 Outline Graphical Models Probabilistic Inference Directed vs.

More information

Data Mining 2018 Bayesian Networks (1)

Data Mining 2018 Bayesian Networks (1) Data Mining 2018 Bayesian Networks (1) Ad Feelders Universiteit Utrecht Ad Feelders ( Universiteit Utrecht ) Data Mining 1 / 49 Do you like noodles? Do you like noodles? Race Gender Yes No Black Male 10

More information

Summary of the Bayes Net Formalism. David Danks Institute for Human & Machine Cognition

Summary of the Bayes Net Formalism. David Danks Institute for Human & Machine Cognition Summary of the Bayes Net Formalism David Danks Institute for Human & Machine Cognition Bayesian Networks Two components: 1. Directed Acyclic Graph (DAG) G: There is a node for every variable D: Some nodes

More information

Naïve Bayes classification. p ij 11/15/16. Probability theory. Probability theory. Probability theory. X P (X = x i )=1 i. Marginal Probability

Naïve Bayes classification. p ij 11/15/16. Probability theory. Probability theory. Probability theory. X P (X = x i )=1 i. Marginal Probability Probability theory Naïve Bayes classification Random variable: a variable whose possible values are numerical outcomes of a random phenomenon. s: A person s height, the outcome of a coin toss Distinguish

More information

Introduction to Probabilistic Graphical Models

Introduction to Probabilistic Graphical Models Introduction to Probabilistic Graphical Models Sargur Srihari srihari@cedar.buffalo.edu 1 Topics 1. What are probabilistic graphical models (PGMs) 2. Use of PGMs Engineering and AI 3. Directionality in

More information

Learning latent structure in complex networks

Learning latent structure in complex networks Learning latent structure in complex networks Lars Kai Hansen www.imm.dtu.dk/~lkh Current network research issues: Social Media Neuroinformatics Machine learning Joint work with Morten Mørup, Sune Lehmann

More information

Learning in Bayesian Networks

Learning in Bayesian Networks Learning in Bayesian Networks Florian Markowetz Max-Planck-Institute for Molecular Genetics Computational Molecular Biology Berlin Berlin: 20.06.2002 1 Overview 1. Bayesian Networks Stochastic Networks

More information

Representation. Stefano Ermon, Aditya Grover. Stanford University. Lecture 2

Representation. Stefano Ermon, Aditya Grover. Stanford University. Lecture 2 Representation Stefano Ermon, Aditya Grover Stanford University Lecture 2 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 2 1 / 32 Learning a generative model We are given a training

More information

Bayesian Networks. Marcello Cirillo PhD Student 11 th of May, 2007

Bayesian Networks. Marcello Cirillo PhD Student 11 th of May, 2007 Bayesian Networks Marcello Cirillo PhD Student 11 th of May, 2007 Outline General Overview Full Joint Distributions Bayes' Rule Bayesian Network An Example Network Everything has a cost Learning with Bayesian

More information

Mixtures of Gaussians. Sargur Srihari

Mixtures of Gaussians. Sargur Srihari Mixtures of Gaussians Sargur srihari@cedar.buffalo.edu 1 9. Mixture Models and EM 0. Mixture Models Overview 1. K-Means Clustering 2. Mixtures of Gaussians 3. An Alternative View of EM 4. The EM Algorithm

More information

STAT 598L Probabilistic Graphical Models. Instructor: Sergey Kirshner. Bayesian Networks

STAT 598L Probabilistic Graphical Models. Instructor: Sergey Kirshner. Bayesian Networks STAT 598L Probabilistic Graphical Models Instructor: Sergey Kirshner Bayesian Networks Representing Joint Probability Distributions 2 n -1 free parameters Reducing Number of Parameters: Conditional Independence

More information

Learning Bayesian network : Given structure and completely observed data

Learning Bayesian network : Given structure and completely observed data Learning Bayesian network : Given structure and completely observed data Probabilistic Graphical Models Sharif University of Technology Spring 2017 Soleymani Learning problem Target: true distribution

More information

Probabilistic Graphical Models

Probabilistic Graphical Models Probabilistic Graphical Models David Sontag New York University Lecture 4, February 16, 2012 David Sontag (NYU) Graphical Models Lecture 4, February 16, 2012 1 / 27 Undirected graphical models Reminder

More information

Review: Bayesian learning and inference

Review: Bayesian learning and inference Review: Bayesian learning and inference Suppose the agent has to make decisions about the value of an unobserved query variable X based on the values of an observed evidence variable E Inference problem:

More information

On the errors introduced by the naive Bayes independence assumption

On the errors introduced by the naive Bayes independence assumption On the errors introduced by the naive Bayes independence assumption Author Matthijs de Wachter 3671100 Utrecht University Master Thesis Artificial Intelligence Supervisor Dr. Silja Renooij Department of

More information

CHAPTER-17. Decision Tree Induction

CHAPTER-17. Decision Tree Induction CHAPTER-17 Decision Tree Induction 17.1 Introduction 17.2 Attribute selection measure 17.3 Tree Pruning 17.4 Extracting Classification Rules from Decision Trees 17.5 Bayesian Classification 17.6 Bayes

More information

LEARNING WITH BAYESIAN NETWORKS

LEARNING WITH BAYESIAN NETWORKS LEARNING WITH BAYESIAN NETWORKS Author: David Heckerman Presented by: Dilan Kiley Adapted from slides by: Yan Zhang - 2006, Jeremy Gould 2013, Chip Galusha -2014 Jeremy Gould 2013Chip Galus May 6th, 2016

More information

Undirected Graphical Models

Undirected Graphical Models Undirected Graphical Models 1 Conditional Independence Graphs Let G = (V, E) be an undirected graph with vertex set V and edge set E, and let A, B, and C be subsets of vertices. We say that C separates

More information

Introduction to Graphical Models

Introduction to Graphical Models Introduction to Graphical Models The 15 th Winter School of Statistical Physics POSCO International Center & POSTECH, Pohang 2018. 1. 9 (Tue.) Yung-Kyun Noh GENERALIZATION FOR PREDICTION 2 Probabilistic

More information

Conditional Independence

Conditional Independence Conditional Independence Sargur Srihari srihari@cedar.buffalo.edu 1 Conditional Independence Topics 1. What is Conditional Independence? Factorization of probability distribution into marginals 2. Why

More information

Inference and estimation in probabilistic time series models

Inference and estimation in probabilistic time series models 1 Inference and estimation in probabilistic time series models David Barber, A Taylan Cemgil and Silvia Chiappa 11 Time series The term time series refers to data that can be represented as a sequence

More information

Learning Terminological Naïve Bayesian Classifiers Under Different Assumptions on Missing Knowledge

Learning Terminological Naïve Bayesian Classifiers Under Different Assumptions on Missing Knowledge Learning Terminological Naïve Bayesian Classifiers Under Different Assumptions on Missing Knowledge Pasquale Minervini Claudia d Amato Nicola Fanizzi Department of Computer Science University of Bari URSW

More information

Prof. Dr. Ralf Möller Dr. Özgür L. Özçep Universität zu Lübeck Institut für Informationssysteme. Tanya Braun (Exercises)

Prof. Dr. Ralf Möller Dr. Özgür L. Özçep Universität zu Lübeck Institut für Informationssysteme. Tanya Braun (Exercises) Prof. Dr. Ralf Möller Dr. Özgür L. Özçep Universität zu Lübeck Institut für Informationssysteme Tanya Braun (Exercises) Slides taken from the presentation (subset only) Learning Statistical Models From

More information

Bayesian Learning in Undirected Graphical Models

Bayesian Learning in Undirected Graphical Models Bayesian Learning in Undirected Graphical Models Zoubin Ghahramani Gatsby Computational Neuroscience Unit University College London, UK http://www.gatsby.ucl.ac.uk/ Work with: Iain Murray and Hyun-Chul

More information

Recall from last time. Lecture 3: Conditional independence and graph structure. Example: A Bayesian (belief) network.

Recall from last time. Lecture 3: Conditional independence and graph structure. Example: A Bayesian (belief) network. ecall from last time Lecture 3: onditional independence and graph structure onditional independencies implied by a belief network Independence maps (I-maps) Factorization theorem The Bayes ball algorithm

More information

NetBox: A Probabilistic Method for Analyzing Market Basket Data

NetBox: A Probabilistic Method for Analyzing Market Basket Data NetBox: A Probabilistic Method for Analyzing Market Basket Data José Miguel Hernández-Lobato joint work with Zoubin Gharhamani Department of Engineering, Cambridge University October 22, 2012 J. M. Hernández-Lobato

More information

Partially Directed Graphs and Conditional Random Fields. Sargur Srihari

Partially Directed Graphs and Conditional Random Fields. Sargur Srihari Partially Directed Graphs and Conditional Random Fields Sargur srihari@cedar.buffalo.edu 1 Topics Conditional Random Fields Gibbs distribution and CRF Directed and Undirected Independencies View as combination

More information

Probability and Information Theory. Sargur N. Srihari

Probability and Information Theory. Sargur N. Srihari Probability and Information Theory Sargur N. srihari@cedar.buffalo.edu 1 Topics in Probability and Information Theory Overview 1. Why Probability? 2. Random Variables 3. Probability Distributions 4. Marginal

More information

Machine Learning. Gaussian Mixture Models. Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall

Machine Learning. Gaussian Mixture Models. Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall Machine Learning Gaussian Mixture Models Zhiyao Duan & Bryan Pardo, Machine Learning: EECS 349 Fall 2012 1 The Generative Model POV We think of the data as being generated from some process. We assume

More information

p L yi z n m x N n xi

p L yi z n m x N n xi y i z n x n N x i Overview Directed and undirected graphs Conditional independence Exact inference Latent variables and EM Variational inference Books statistical perspective Graphical Models, S. Lauritzen

More information

Conditional Random Field

Conditional Random Field Introduction Linear-Chain General Specific Implementations Conclusions Corso di Elaborazione del Linguaggio Naturale Pisa, May, 2011 Introduction Linear-Chain General Specific Implementations Conclusions

More information

PMR Learning as Inference

PMR Learning as Inference Outline PMR Learning as Inference Probabilistic Modelling and Reasoning Amos Storkey Modelling 2 The Exponential Family 3 Bayesian Sets School of Informatics, University of Edinburgh Amos Storkey PMR Learning

More information

CS37300 Class Notes. Jennifer Neville, Sebastian Moreno, Bruno Ribeiro

CS37300 Class Notes. Jennifer Neville, Sebastian Moreno, Bruno Ribeiro CS37300 Class Notes Jennifer Neville, Sebastian Moreno, Bruno Ribeiro 2 Background on Probability and Statistics These are basic definitions, concepts, and equations that should have been covered in your

More information

ECE521 Tutorial 11. Topic Review. ECE521 Winter Credits to Alireza Makhzani, Alex Schwing, Rich Zemel and TAs for slides. ECE521 Tutorial 11 / 4

ECE521 Tutorial 11. Topic Review. ECE521 Winter Credits to Alireza Makhzani, Alex Schwing, Rich Zemel and TAs for slides. ECE521 Tutorial 11 / 4 ECE52 Tutorial Topic Review ECE52 Winter 206 Credits to Alireza Makhzani, Alex Schwing, Rich Zemel and TAs for slides ECE52 Tutorial ECE52 Winter 206 Credits to Alireza / 4 Outline K-means, PCA 2 Bayesian

More information

Events A and B are independent P(A) = P(A B) = P(A B) / P(B)

Events A and B are independent P(A) = P(A B) = P(A B) / P(B) Events A and B are independent A B U P(A) = P(A B) = P(A B) / P(B) 1 Alternative Characterization of Independence a) P(A B) = P(A) b) P(A B) = P(A) P(B) Recall P(A B) = P(A B) / P(B) (if P(B) 0) So P(A

More information

CS 484 Data Mining. Classification 7. Some slides are from Professor Padhraic Smyth at UC Irvine

CS 484 Data Mining. Classification 7. Some slides are from Professor Padhraic Smyth at UC Irvine CS 484 Data Mining Classification 7 Some slides are from Professor Padhraic Smyth at UC Irvine Bayesian Belief networks Conditional independence assumption of Naïve Bayes classifier is too strong. Allows

More information

Representation of undirected GM. Kayhan Batmanghelich

Representation of undirected GM. Kayhan Batmanghelich Representation of undirected GM Kayhan Batmanghelich Review Review: Directed Graphical Model Represent distribution of the form ny p(x 1,,X n = p(x i (X i i=1 Factorizes in terms of local conditional probabilities

More information

9/12/17. Types of learning. Modeling data. Supervised learning: Classification. Supervised learning: Regression. Unsupervised learning: Clustering

9/12/17. Types of learning. Modeling data. Supervised learning: Classification. Supervised learning: Regression. Unsupervised learning: Clustering Types of learning Modeling data Supervised: we know input and targets Goal is to learn a model that, given input data, accurately predicts target data Unsupervised: we know the input only and want to make

More information

Part I. C. M. Bishop PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS

Part I. C. M. Bishop PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS Part I C. M. Bishop PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 8: GRAPHICAL MODELS Probabilistic Graphical Models Graphical representation of a probabilistic model Each variable corresponds to a

More information

Bayesian Machine Learning

Bayesian Machine Learning Bayesian Machine Learning Andrew Gordon Wilson ORIE 6741 Lecture 4 Occam s Razor, Model Construction, and Directed Graphical Models https://people.orie.cornell.edu/andrew/orie6741 Cornell University September

More information

Motivation. Bayesian Networks in Epistemology and Philosophy of Science Lecture. Overview. Organizational Issues

Motivation. Bayesian Networks in Epistemology and Philosophy of Science Lecture. Overview. Organizational Issues Bayesian Networks in Epistemology and Philosophy of Science Lecture 1: Bayesian Networks Center for Logic and Philosophy of Science Tilburg University, The Netherlands Formal Epistemology Course Northern

More information

Graphical models and causality: Directed acyclic graphs (DAGs) and conditional (in)dependence

Graphical models and causality: Directed acyclic graphs (DAGs) and conditional (in)dependence Graphical models and causality: Directed acyclic graphs (DAGs) and conditional (in)dependence General overview Introduction Directed acyclic graphs (DAGs) and conditional independence DAGs and causal effects

More information

T Machine Learning: Basic Principles

T Machine Learning: Basic Principles Machine Learning: Basic Principles Bayesian Networks Laboratory of Computer and Information Science (CIS) Department of Computer Science and Engineering Helsinki University of Technology (TKK) Autumn 2007

More information

Lecture 15. Probabilistic Models on Graph

Lecture 15. Probabilistic Models on Graph Lecture 15. Probabilistic Models on Graph Prof. Alan Yuille Spring 2014 1 Introduction We discuss how to define probabilistic models that use richly structured probability distributions and describe how

More information

{ p if x = 1 1 p if x = 0

{ p if x = 1 1 p if x = 0 Discrete random variables Probability mass function Given a discrete random variable X taking values in X = {v 1,..., v m }, its probability mass function P : X [0, 1] is defined as: P (v i ) = Pr[X =

More information

MATHEMATICS. Units Topics Marks I Relations and Functions 10

MATHEMATICS. Units Topics Marks I Relations and Functions 10 MATHEMATICS Course Structure Units Topics Marks I Relations and Functions 10 II Algebra 13 III Calculus 44 IV Vectors and 3-D Geometry 17 V Linear Programming 6 VI Probability 10 Total 100 Course Syllabus

More information

Recall from last time: Conditional probabilities. Lecture 2: Belief (Bayesian) networks. Bayes ball. Example (continued) Example: Inference problem

Recall from last time: Conditional probabilities. Lecture 2: Belief (Bayesian) networks. Bayes ball. Example (continued) Example: Inference problem Recall from last time: Conditional probabilities Our probabilistic models will compute and manipulate conditional probabilities. Given two random variables X, Y, we denote by Lecture 2: Belief (Bayesian)

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning Undirected Graphical Models Mark Schmidt University of British Columbia Winter 2016 Admin Assignment 3: 2 late days to hand it in today, Thursday is final day. Assignment 4:

More information

Introduction to Bayesian inference

Introduction to Bayesian inference Introduction to Bayesian inference Thomas Alexander Brouwer University of Cambridge tab43@cam.ac.uk 17 November 2015 Probabilistic models Describe how data was generated using probability distributions

More information

4.1 Notation and probability review

4.1 Notation and probability review Directed and undirected graphical models Fall 2015 Lecture 4 October 21st Lecturer: Simon Lacoste-Julien Scribe: Jaime Roquero, JieYing Wu 4.1 Notation and probability review 4.1.1 Notations Let us recall

More information

Basic Sampling Methods

Basic Sampling Methods Basic Sampling Methods Sargur Srihari srihari@cedar.buffalo.edu 1 1. Motivation Topics Intractability in ML How sampling can help 2. Ancestral Sampling Using BNs 3. Transforming a Uniform Distribution

More information

3 : Representation of Undirected GM

3 : Representation of Undirected GM 10-708: Probabilistic Graphical Models 10-708, Spring 2016 3 : Representation of Undirected GM Lecturer: Eric P. Xing Scribes: Longqi Cai, Man-Chia Chang 1 MRF vs BN There are two types of graphical models:

More information

Probabilistic Graphical Models

Probabilistic Graphical Models Probabilistic Graphical Models Lecture 4 Learning Bayesian Networks CS/CNS/EE 155 Andreas Krause Announcements Another TA: Hongchao Zhou Please fill out the questionnaire about recitations Homework 1 out.

More information

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari Deep Belief Nets Sargur N. Srihari srihari@cedar.buffalo.edu Topics 1. Boltzmann machines 2. Restricted Boltzmann machines 3. Deep Belief Networks 4. Deep Boltzmann machines 5. Boltzmann machines for continuous

More information

Bayesian Networks Representation

Bayesian Networks Representation Bayesian Networks Representation Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University March 19 th, 2007 Handwriting recognition Character recognition, e.g., kernel SVMs a c z rr r r

More information

Classical Predictive Models

Classical Predictive Models Laplace Max-margin Markov Networks Recent Advances in Learning SPARSE Structured I/O Models: models, algorithms, and applications Eric Xing epxing@cs.cmu.edu Machine Learning Dept./Language Technology

More information

10708 Graphical Models: Homework 2

10708 Graphical Models: Homework 2 10708 Graphical Models: Homework 2 Due Monday, March 18, beginning of class Feburary 27, 2013 Instructions: There are five questions (one for extra credit) on this assignment. There is a problem involves

More information

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2016

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2016 Bayesian Networks: Construction, Inference, Learning and Causal Interpretation Volker Tresp Summer 2016 1 Introduction So far we were mostly concerned with supervised learning: we predicted one or several

More information

Bridging the two cultures: Latent variable statistical modeling with boosted regression trees

Bridging the two cultures: Latent variable statistical modeling with boosted regression trees Bridging the two cultures: Latent variable statistical modeling with boosted regression trees Thomas G. Dietterich and Rebecca Hutchinson Oregon State University Corvallis, Oregon, USA 1 A Species Distribution

More information

Bayesian Networks BY: MOHAMAD ALSABBAGH

Bayesian Networks BY: MOHAMAD ALSABBAGH Bayesian Networks BY: MOHAMAD ALSABBAGH Outlines Introduction Bayes Rule Bayesian Networks (BN) Representation Size of a Bayesian Network Inference via BN BN Learning Dynamic BN Introduction Conditional

More information

Bayesian Networks Introduction to Machine Learning. Matt Gormley Lecture 24 April 9, 2018

Bayesian Networks Introduction to Machine Learning. Matt Gormley Lecture 24 April 9, 2018 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Bayesian Networks Matt Gormley Lecture 24 April 9, 2018 1 Homework 7: HMMs Reminders

More information

Online Bayesian Passive-Agressive Learning

Online Bayesian Passive-Agressive Learning Online Bayesian Passive-Agressive Learning International Conference on Machine Learning, 2014 Tianlin Shi Jun Zhu Tsinghua University, China 21 August 2015 Presented by: Kyle Ulrich Introduction Online

More information

Bayesian Networks. Motivation

Bayesian Networks. Motivation Bayesian Networks Computer Sciences 760 Spring 2014 http://pages.cs.wisc.edu/~dpage/cs760/ Motivation Assume we have five Boolean variables,,,, The joint probability is,,,, How many state configurations

More information

Probabilistic Time Series Classification

Probabilistic Time Series Classification Probabilistic Time Series Classification Y. Cem Sübakan Boğaziçi University 25.06.2013 Y. Cem Sübakan (Boğaziçi University) M.Sc. Thesis Defense 25.06.2013 1 / 54 Problem Statement The goal is to assign

More information