time-varying networks inference and structured input-out ...epxing/ic/cs-ic08.pdf · statistical...

28
1 Eric Xing Eric Xing ML/LTI/CSD School of Computer Science Carnegie Mellon University Time Time - - Varying Networks Varying Networks Inference Inference and and Structured Input Structured Input - - Out Learning Out Learning http://www.sailing.cs.cmu.edu/

Upload: nguyennhu

Post on 14-Aug-2019

216 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

1

Eric XingEric Xing

ML/LTI/CSDSchool of Computer ScienceCarnegie Mellon University

TimeTime--Varying NetworksVarying Networks InferenceInferenceand and

Structured InputStructured Input--Out LearningOut Learning

http://www.sailing.cs.cmu.edu/

Page 2: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

2

Learning in structured input/output spaceSemi-supervised and unsupervised maximum margin learningTheory and algorithm for optimization, inference and active learningApplications in genomics, machine translation, and multi-media analysis

Nonparametric Bayesian models for "open worlds"Domain-closure, unique name and stationarity assumptions are not always valid:

How many clusters/states/objects/relations out there?Ambiguous data association.Birth/death/evolution of possible worlds.

Infinite-capacity models based on Dirichlet process (Polya urn schemes)Applications in genetics and evolution, tracking and email filtering

Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics of networksInferring their semantic aspects, missing links, and node attributesBiological and social network analysis

Overview:Overview:Learning and Reasoning under UncertaintyLearning and Reasoning under Uncertainty

(Xing, et al. ICML 04,06, Ahmed SDM08)

(zen, et al. KDD 07, Zhu, et al, ICML08, Kim, UAI08)

(Guo, et al. ICML 07)

Genomics and regulatory evolutionStatistical models for genome evolution and natural selectionFunctional effects on gene regulation and morphogenesis Gene finding and functional prediction via comparative genomic analysis

Computation Developmental Biology of FlysImage analysis and database

Feature processing, segmentation, and pattern representationRecovering 3D structure from 2D imagesShape and deformation modeling and categorization

Spatial-temporal modeling of gene regulationTemporal shape evolution and models for morphogenesisThe genetics of pattern polymorphism and divergence

Genetic variation and diseases associationGenealogy/evolution models: how many founders, migration and evolution history...Models for linkages between variations and phenotypesClinical and forensic applications

++++

Overview: Overview: Computational Biology and Statistical GeneticsComputational Biology and Statistical Genetics

Page 3: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

3

9/8/2006, CALD IC

Novel Statistical Models and Algorithms for Network Novel Statistical Models and Algorithms for Network Modeling, Mining, and Reverse EngineeringModeling, Mining, and Reverse Engineering

NSF IIS-0713379

PI: Eric Xing

Inferring TimeInferring Time--VaryingVarying

NetworksNetworks

Disease Spread

Social Network

Food Web

Citation Network

Internet

Network and Relational DataNetwork and Relational Data

Page 4: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

4

Changing Social Networks In Changing Social Networks In WashingtonWashington

Corporativity,

Antagonism,

Cliques,…

over time?

T0 TN ?…

"Rewiring" Pathways in Biology"Rewiring" Pathways in Biology

Page 5: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

5

Problem: Network reconstruction Problem: Network reconstruction

Reverse engineer "rewiring" networks

Temporal Exponential Random Graph Temporal Exponential Random Graph ModelsModels

( ) ( ) ( ){ }111 ,ln,exp −−− −Ψ⋅= ttttt AZAAAAP θθ

Markov Markov aassumptionssumption::

TimeTime--evolving network model:evolving network model:

( ) ( ) ( ) ( )1121121 APAAPAAPAAAAP tttt ,,,, LK −− =

Page 6: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

6

"Dynamic" Potentials"Dynamic" Potentials

“Continuity”:

“Reciprocity”:

“Transitivity”:

“Density”:

( ) ( )( )( )∑ −−− −−+=Ψij

tij

tij

tij

tij

tt AAAAAA 1111 11,

( ) ( ) ( ){ }111 ,ln,exp −−− −Ψ⋅= ttttt AZAAAAP θθ

( ) ∑ −− =Ψij

tji

tij

tt AAAA 112 ,

( )∑∑

−−

−−

− =Ψijk

tkj

tik

ijktkj

tik

tijtt

AA

AAAAA 11

111

3 ,

( ) ∑=Ψ −

ij

tij

tt AAA 14 ,

Degeneracy Degeneracy (Handcock et al.)(Handcock et al.)

Some estimator can result in an ERGM that place most of the probability mass on a subset of the sample space containing networks that bear no resemblance to the observed networks

For such models, an MLE does not exist, resulting in poor fite.g., When the observed statistics do not lie inside of the convex hull of the set of all realizable u(A).

Page 7: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

7

A A tERGMtERGM is nonis non--degenerate degenerate

Theorem: when the transition distribution factors over the edges, a tERGM is non-degenerate:

Straightforward -- tractable transition model; the partition function is the product of per edge terms

Computation is non-trivial

Given the graphical structure, run variable elimination algorithms, works well only for small graphs

InferenceInference (1)(1)

Gibbs sampling:

Need to evaluate the log-odds

Difficulty: Evaluate the ratio of Partition function Z(A')=ΣAexp(θΦ(A,A'))So far scale to ~20 genes

P(Network|Data) ?

Page 8: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

8

TESLA: Temporally Smoothed L1-regularized logistic regression

Constrained convex optimizationNow scale to ~5000 genes, how about 20K+ ?

InferenceInference (2)(2)

Page 9: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

9

T=1

molecular function

biological process

cellular component

T=2

Page 10: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

10

T=3

T=4

Page 11: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

11

T=5

T=6

Page 12: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

12

T=7

T=8

Page 13: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

13

T=9

T=10

Page 14: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

14

T=11

T=12

Page 15: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

15

T=13

T=14

Page 16: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

16

T=15

T=16

Page 17: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

17

T=17

T=18

Page 18: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

18

T=19

T=20

Page 19: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

19

T=21

T=22

Page 20: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

20

T=23

Transient InteractionTransient Interaction

Page 21: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

21

NIPS academic social networkNIPS academic social network

1987

1988

1998

1999

Open theoretical issues and on-going and future workApproximating Z in hTERGM

Scalability of network inference algorithm

Statistical guarantees on the estimates– Consistence (pattern, value, …)

– Confidence

– Stability

– Sample complexity

Applications:Reconstructing Temporally Rewiring Genetic Interactions During the Life Cycle of Drosophila melanogasterAuthor-paper networks in scientific literature

Open IssuesOpen Issues

Page 22: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

22

Other Other ProblemProblemss: : Dynamic Dynamic Node ClusteringNode Clustering

Other Other ProblemProblemss: Network Alignment : Network Alignment

Corporate merging

+ = ?

Company A Company B

Page 23: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

23

Our GoalsOur Goals

Develop new methods for latent theme distillation and data integration for network data.

Mixed Membership of Stochastic Blocks [Airoldi, Blei, Fienberg and Xing, 2005, 2006, 2007]

Develop new formalisms for modeling network evolution over time;and techniques for reverse engineering unobserved temporally rewiring networks from time series of entity attributes.

Temporal Exponential Random Graph Model [Hanneke and Xing, 2006]Hidden Temporal Exponential Random Graph Model [Guo, Hanneke, Fu and Xing, 2007]

Develop new algorithms for predicting the global topology of very large networks based on randomly sampled subnetworks; and investigate confidence guarantees.

Modern view

ACGTTTTACTGTACAATT

Traditional view

ACGTTTTACTGTACAATT

a a univariateunivariate phenotype:phenotype:

i.e., disease/controli.e., disease/control

Multivariate complex syndrome (e.g., asthma):Multivariate complex syndrome (e.g., asthma):age at onset, age at onset, presence/absence of presence/absence of eosinophiliceosinophilic inflammation, inflammation, history of eczemahistory of eczemagenomegenome--wide expression profilewide expression profile……

causal SNPcausal SNPcausal SNP networkscausal SNP networks

GenomeGenome--Phenome AssociationPhenome Associationand and Structured InputStructured Input--Out LearningOut Learning

Page 24: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

24

Example: the asthma phenotype networkExample: the asthma phenotype network

Genome and Phenome StructuresGenome and Phenome Structures

Modern view

ACGTTTTACTGTACAATT

Traditional view

ACGTTTTACTGTACAATT

•• PairPair--wise association tests?wise association tests?– Ignore SNP dependencies– Many many FPs

•• Regression?Regression?– Over-stringent on coupled SNPs

•• Structured regularized regressionStructured regularized regression

explicitly capture structuresefficientsparse (parsimonious)provable guarantees

Goad: Goad: Inferring GenomeInferring Genome--Phenome Phenome AssociationAssociation

Page 25: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

25

General Structured PredictionGeneral Structured Prediction

Inputs:a set of training samples: , where

Application ExamplesPart-of-speech (POS) Tagging:

Image Segmentation:

Outputs:a predictive function :

“Do you want sugar in it?” ⇒ <verb pron verb noun prep pron>

ACGTTTTACTGTACAATT

Overall effect of the weighted fusion penalty

Step 1: Thresholded correlation graph of phenotypes with weights

ACGTTTTACTGTACAATT

Step 2: Graph-weighted fused lasso

Weighted Fusion

GraphGraph--Weighted Fused LassoWeighted Fused Lasso

Page 26: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

26

Phenotype Correlation Structure

Single-marker Single-trait test

LassoGraph-weighted Fused lasso

Asthma MultipleAsthma Multiple--trait Associationtrait Association

?

MarginMargin--Based Discriminative Learning Based Discriminative Learning ParadigmsParadigms

SVM SVM b r a c e

M3N

MED MED

M3N

MED-MN= SMED + Bayesian M3N

Page 27: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

27

Maximum Entropy Discrimination Maximum Entropy Discrimination Markov NetworksMarkov Networks

Structured MaxEnt Discrimination (SMED):

Feasible subspace of weight distribution:

Bayesian M3N

Generalization GuaranteeGeneralization Guarantee

MaxEntNet is an averaging model– we also call it a Bayesian Max-Margin Markov Network

Theorem (PAC-Bayes Bound)

If

Then

Page 28: Time-Varying Networks Inference and Structured Input-Out ...epxing/IC/CS-ic08.pdf · Statistical modeling and inference of relational data Modeling the formation, evolution, and dynamics

28

Key ChallengesKey Challenges

Extremely high dimensionality and low data volumed ~ 1MN ~ 1KSample complexity with bounded error?

Sparsity bias of the modelOften <100 features out of the !M are relevant Regularization schemes to enforce sparsity

Structures and hidden variablesInputs and outputs often bear intricate structures (e.g., chain or graphical dependencies)How to capture other latent structures between unobserved variables

Generalizability and scalabilityMove efficient convex opt solver and Bayesian inference algorithms

Provable theoretical guaranteesConsistency and sparsistencyStability, convergence rate, etc.