impact of structuring on bayesian network learning and reasoning

41
Impact of Structuring on Bayesian Network Learning and Reasoning Mieczysław.A..Kłopotek Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland, First Warsaw International Seminar on Soft Computing Warsaw, September 8th, 2003

Upload: geordi

Post on 06-Jan-2016

29 views

Category:

Documents


4 download

DESCRIPTION

Impact of Structuring on Bayesian Network Learning and Reasoning. M ieczysław .A. .K ł opotek Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland,. First Warsaw International Seminar on Soft Computing Warsaw, September 8th, 2003. Agenda. Definitions - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Impact of Structuring on Bayesian Network Learning and Reasoning

1

Impact of Structuring on Bayesian Network Learning

and Reasoning

Mieczysław.A..Kłopotek

Institute of Computer Science,

Polish Academy of Sciences,

Warsaw, Poland,

First Warsaw International Seminar on Soft Computing Warsaw, September 8th, 2003

Page 2: Impact of Structuring on Bayesian Network Learning and Reasoning

2

2

Agenda

Definitions Approximate Reasoning Bayesian networks

Reasoning in Bayesian networks Learning Bayesian networks from data Structured Bayesian networks (SBN) Reasoning in SBN Learning SBN from data Concluding remarks

Page 3: Impact of Structuring on Bayesian Network Learning and Reasoning

3

3

Approximate Reasoning One possible method of expressing uncertainty: Joint

Probability Distribution Variables: causes, effects, observables Reasoning: How probable is that a variable takes a given

value if we kniow the values of some other variables Given: P(X,Y,....,Z) Find: P(X=x | T=t,...,W=w)

Difficult, if more than 40 variables have to be taken into account hard to represent, hard to reason, hard to collect data)

Page 4: Impact of Structuring on Bayesian Network Learning and Reasoning

4

4

The method of choice for representing uncertainty in AI.

Many efficient reasoning methods and learning methods

Utilize explicit representation of structure to: provide a natural and compact

representation of large probability distributions.

allow for efficient methods for answering a wide range of queries.

Bayesian Network

Page 5: Impact of Structuring on Bayesian Network Learning and Reasoning

5

5

Bayesian Network Efficient and effective representation of a

probability distribution Directed acyclic graph

Nodes - random variables of interests Edges - direct (causal) influence

Nodes are statistically independent of their non descendants given the state of their parents

Page 6: Impact of Structuring on Bayesian Network Learning and Reasoning

6

6

A Bayesian network

R

Z

T

Y

X

S

Pr(r,s,x,z,y)=

Pr(z) . Pr(s|z) . Pr(y|z)

. Pr(x|y) . Pr(r|y,s)

Page 7: Impact of Structuring on Bayesian Network Learning and Reasoning

7

7

Applications of Bayesian networks Genetic optimization algorithms with

probabilistic mutation/crossing mechanism Classification, including text classification Medical diagnosis (PathFinder, QMR), other

decision making tasks under uncertainty Hardware diagnosis (Microsoft troubleshooter,

NASA/Rockwell Vista project) Information retrieval (Ricoh helpdesk) Recommender systems other

Page 8: Impact of Structuring on Bayesian Network Learning and Reasoning

8

8

Reasoning – the problem with a Bayesian network Fusion algorithm of Pearl elaborated for tree-like

networks only For other types of networks transformations to

trees: transformation to Markov tree (MT) is needed

(Shafer/Shenoy, Spiegelhalter/Lauritzen) – except for trees and polytrees NP hard

Cutset reasoning (Pearl) – finding cutsets difficult, the reasoning complexity grows exponentially with cutset size needed

evidence absorption reasoning by edge reversal (Shachter) – not always possible in a simple way

Page 9: Impact of Structuring on Bayesian Network Learning and Reasoning

9

9

Towards MT – moral graph

R

Z

T

Y

X

S

Parents of a node in BN connected, edges not oriented

Page 10: Impact of Structuring on Bayesian Network Learning and Reasoning

10

10

Towards MT – triangulated graph

R

Z

T

Y

X

S

All cycles with more than 3 nodes have at least one link between non-neighboring nodes of the cycle.

Page 11: Impact of Structuring on Bayesian Network Learning and Reasoning

11

11

Towards MT – Hypertree

R

Z

T

Y

X

S

Hypertree = acyclic hypergraph

Page 12: Impact of Structuring on Bayesian Network Learning and Reasoning

12

12

The Markov tree

Z,T,Y T,Y,S Y,S,R

Y,X

Hypernodes of hypertree are nodes of the Markov tree

Page 13: Impact of Structuring on Bayesian Network Learning and Reasoning

13

13

Junction tree – alternative representation of MT

Z,T,S Z,Y,S Y,S,R

Y,X

Z,S Y,S

Y

Common BN nodes assigned to edges joining MT nodes

Page 14: Impact of Structuring on Bayesian Network Learning and Reasoning

14

14

Efficient reasoning in Markov trees, but ....

Z,T,S Z,Y,S Y,S,R

Y,X

Z,S Y,S

Y

msg msg

msg

MT node contents projected onto common variables are passed to the neighbors

Page 15: Impact of Structuring on Bayesian Network Learning and Reasoning

15

15

Triangulability test - Triangulation not always possible

All neighbors need to be connected

Page 16: Impact of Structuring on Bayesian Network Learning and Reasoning

16

16

Evidence absorption reasoning

R

Z

T

Y

X

S

R

Z

T

Y

X

S

Evidence absorption

R

Z

T

Y

X

S

Edge reversal

Efficient only for good-luck selection of conditioning variables

Page 17: Impact of Structuring on Bayesian Network Learning and Reasoning

17

17

Cutset reasoning – fixing values of some nodes creates a (poly)tree

R

Z

T

Y

X

S

Node fixed

Hence edge ignorable

Page 18: Impact of Structuring on Bayesian Network Learning and Reasoning

18

18

How to overcome the difficulty when reasoning with BN Learn directly a triangulated graph or Markov tree

from data (Cercone N., Wong S.K.M., Xiang Y) Hard and inefficient for long dependence chains,

danger of large hypernodes Learn only tree-structured/polytree structured BN

(e.g. In Goldberg’s Bayesian Genetic Algorithms, TAN text classifiers etc.) Oversimplification, long dependence chains lost

Our approach: Propose a more general class of Bayesian networks that is still efficient for reasoning

Page 19: Impact of Structuring on Bayesian Network Learning and Reasoning

19

19

What is a structured Bayesian network An analogon of well-structured

programs Graphical structure: nested sequences

and alternatives By collapsing sequences and

alternatives to single nodes, one single node obtainable

Efficient reasoning possible

Page 20: Impact of Structuring on Bayesian Network Learning and Reasoning

20

20

Structured Bayesian Network (SBN), an example

For comparison: a tree-structured BN

Page 21: Impact of Structuring on Bayesian Network Learning and Reasoning

21

21

SBN collapsing

Page 22: Impact of Structuring on Bayesian Network Learning and Reasoning

22

22

SBN construction steps

means 0,1 or 2 arrows

Page 23: Impact of Structuring on Bayesian Network Learning and Reasoning

23

23

Reasoning in SBN

Either directly in the structure Or easily transformable to Markov tree Direct reasoning consisting of

Forward step (leave node/root node valuation calculation)

Backward step (intermediate node valuation calculation

Page 24: Impact of Structuring on Bayesian Network Learning and Reasoning

24

24

Reasoning in SBN forward step

means 0,1 or 2 arrows

A

B

A

B

CEP(B|A)

P(B|C,E)

Page 25: Impact of Structuring on Bayesian Network Learning and Reasoning

25

25

Reasoning in SBN backward step: local context

AC

B

D

.....

.....A

C

B

D

.....

.....A

C

B

.....

.....A

C

B

.....

.....

(a) (b) (c) (d)

Joint distribu-tion of A,B known, joint C,D or C sought

Page 26: Impact of Structuring on Bayesian Network Learning and Reasoning

26

26

Reasoning in SBN – backward step: local reasoning

A,B,............ A,B,C,DA,B

Msg2(A,B)

Msg1(A,B)

P(A)*P(B|A,D)

Not needed

Page 27: Impact of Structuring on Bayesian Network Learning and Reasoning

27

27

SBN –towards a MT

Page 28: Impact of Structuring on Bayesian Network Learning and Reasoning

28

28

SBN –towards a MT

Page 29: Impact of Structuring on Bayesian Network Learning and Reasoning

29

29

SBN –towards a MT

Page 30: Impact of Structuring on Bayesian Network Learning and Reasoning

30

30

B

C D

E

A

J

I

S

R

H

F

G

P

K

L

M N

O

Towards a Markobv tree – an example

Page 31: Impact of Structuring on Bayesian Network Learning and Reasoning

31

31

B

C D

E

A

J

I

S

R

H

F

G

P

K

L

M N

O

Towards a Markobv tree – an example

Page 32: Impact of Structuring on Bayesian Network Learning and Reasoning

32

32

A,B,I

B,C,D,I

C,D,E,I

F,G,I

G,H,I

I,H,E,R D,E,I

E,H,R,J H,R,J

K,L,R

L,M,N,R

M,N,O,R

N,O,R

O,P,R

R,J,P

P,J,S

Markov tree from SBN

Page 33: Impact of Structuring on Bayesian Network Learning and Reasoning

33

33

B

C D

E

A

J

I

S

R

H

F

G

P

K

L

M N

O

Structured Bayesian network – a Hierarchical (Object-Oriented) Bayesian network

Page 34: Impact of Structuring on Bayesian Network Learning and Reasoning

34

34

Learning SBN from Data

Define the DEP() measure as follows:

DEP(Y,X)=P(x|y)-P(x|y).

Define DEP[](Y,X)= (DEP(Y,X) )2

Construct a tree according to Chow/Liu algorithm using DEP[](Y,X) with Y

belonging to the tree and X not.

Page 35: Impact of Structuring on Bayesian Network Learning and Reasoning

35

35

Continued ....

Let us call all the edges obtained by the previous algorithm “free edges”.

During the construction process the following type of edges may additionally appear “node X loop unoriented edge”, “node X loop oriented edge”, “node X loop transient edge”.

Do in a loop (till termination condition below is satisfied):

For each two properly connected non-neighboring nodes identify the unique connecting path between them.

Page 36: Impact of Structuring on Bayesian Network Learning and Reasoning

36

36

Continued ....

Two nodes are properly connected if the path between them consists either of edges having the status of free edges or of oriented, unoriented (but not suspended) edges of the same loop, with no pair of oriented or transient oriented edges pointing in different directions and no transient edge pointing to one of the two connected points.

Note that in this sense there is at most one path properly connecting two nodes.

Page 37: Impact of Structuring on Bayesian Network Learning and Reasoning

37

37

Continued ....

Connect that a pair of non-neighboring nodes X,Y by an edge, that maximizes DEP[](X,Y), the minimum of

unconditional DEP and conditional DEP given a direct successor of X on the path to Y.

Identify the loop that has emerged from this operation.

Page 38: Impact of Structuring on Bayesian Network Learning and Reasoning

38

38

Continued ....

We can have one of the following cases: (1)it consists entirely of free edges (2)it contains some unoriented loop edges, but

no oriented edge. (3)It contains at least one oriented edge. Depending on this, give a proper status to

edges contained in a loop: “node X loop unoriented edge”, “node X loop oriented edge”, “node X loop transient edge”. (details in written presentation).

Page 39: Impact of Structuring on Bayesian Network Learning and Reasoning

39

39

Places of edge insertion

X

C

D

Y

B

Y

C

D

E

X

Y

G

D

E

X

C

Y

C

D

X

B

H

X

C

D

E

Y

X

G

D

E

Y

C

Page 40: Impact of Structuring on Bayesian Network Learning and Reasoning

40

40

Concluding Remarks

new class of Bayesian networks defined completely new method of reasoning in Bayesian

networks outlined Local computation – at most 4 nodes involved applicable to a more general class of networks then

known reasoning methods new class Bayesian networks easily transfornmed to

Markov trees new class Bayesian networks – a kind of hierarchical or

object-oriented Bayesian networks Can be learned from data

Page 41: Impact of Structuring on Bayesian Network Learning and Reasoning

41

41

THANK YOU