SlideShare a Scribd company logo
1 of 35
Download to read offline
Learning LWF Chain Graphs:
A Markov Blanket Discovery Approach
Mohammad Ali Javidian
@ali javidian
Marco Valtorta
@MarcoGV2
Pooyan Jamshidi
@PooyanJamshidi
Department of Computer Science and Engineering
University of South Carolina
UAI 2020
1 / 9
LWF Chain Graphs (CGs)
Chain graphs:
admit both directed and undirected edges,
2 / 9
LWF Chain Graphs (CGs)
Chain graphs:
admit both directed and undirected edges,
there are no partially directed cycles.
2 / 9
LWF Chain Graphs (CGs)
Chain graphs:
admit both directed and undirected edges,
there are no partially directed cycles.
A Partially directed cycle: is a sequence of n distinct vertices
v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t.
for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and
there exists a j (1 ≤ j ≤ n) such that vj ← vj+1.
2 / 9
LWF Chain Graphs (CGs)
Chain graphs:
admit both directed and undirected edges,
there are no partially directed cycles.
A Partially directed cycle: is a sequence of n distinct vertices
v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t.
for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and
there exists a j (1 ≤ j ≤ n) such that vj ← vj+1.
Example:
2 / 9
LWF Chain Graphs (CGs)
Chain graphs:
admit both directed and undirected edges,
there are no partially directed cycles.
A Partially directed cycle: is a sequence of n distinct vertices
v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t.
for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and
there exists a j (1 ≤ j ≤ n) such that vj ← vj+1.
Example:
Chain graphs under different interpretations: LWF, AMP, MVR, ...
Here, we focus on chain graphs (CGs) under the
Lauritzen-Wermuth-Frydenberg (LWF) interpretation.
2 / 9
Markov Blankets Enable Locality in Causal Structure Recovery
H
B
J
ADE
FC
I
OM N
K L
GT 𝑴𝒃(𝑇) H
B
J
ADE
FC
I
OM N
K L
GT
3 / 9
Markov Blankets Enable Locality in Causal Structure Recovery
H
B
J
ADE
FC
I
OM N
K L
GT 𝑴𝒃(𝑇) H
B
J
ADE
FC
I
OM N
K L
GT
3 / 9
Markov Blankets Enable Locality in Causal Structure Recovery
H
B
J
ADE
FC
I
OM N
K L
GT 𝑴𝒃(𝑇) H
B
J
ADE
FC
I
OM N
K L
GT
𝒄𝒉(𝑇)
3 / 9
Markov Blankets Enable Locality in Causal Structure Recovery
H
B
J
ADE
FC
I
OM N
K L
GT 𝑴𝒃(𝑇) H
B
J
ADE
FC
I
OM N
K L
GT
3 / 9
Markov Blankets Enable Locality in Causal Structure Recovery
H
B
J
ADE
FC
I
OM N
K L
GT 𝑴𝒃(𝑇) H
B
J
ADE
FC
I
OM N
K L
GT
Markov blankets can be used as a powerful tool in:
classification,
local causal discovery
3 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
𝒑𝒂(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
𝒄𝒉(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
𝒏𝒆(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
𝒄𝒔𝒑(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem (Characterization of Markov Blankets in LWF CGs)
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target
variable T in an LWF CG probabilistically shields T from the rest of the variables.
5 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem (Characterization of Markov Blankets in LWF CGs)
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target
variable T in an LWF CG probabilistically shields T from the rest of the variables.
Theorem (Standard algorithms for Markov blanket recovery in LWF CGs)
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
5 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem (Characterization of Markov Blankets in LWF CGs)
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target
variable T in an LWF CG probabilistically shields T from the rest of the variables.
Theorem (Standard algorithms for Markov blanket recovery in LWF CGs)
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
The characterization of Markov blankets in chain graphs
enables us to develop new algorithms that are specifically
designed for learning Markov blankets in chain graphs.
5 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
6 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
6 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
Shrink
Phase:
𝐌𝐛(𝑇) H
B
J
A
E
FC
I
M
K L
GT
D
H
B
J
A
E
FC
I
M
K L
GT
D
6 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
Shrink
Phase:
𝐌𝐛(𝑇) H
B
J
A
E
FC
I
M
K L
GT
D
H
B
J
A
E
FC
I
M
K L
GT
D
Such Markov blanket discovery algorithms help
us to design new scalable algorithms for learning
chain graphs based on local structure discovery.
6 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
7 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
A
DC E
B
Super Skeleton
Recovery
7 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
A
DC E
B
Super Skeleton
Recovery
𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵
Skeleton
A
DC E
B
7 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
A
DC E
B
Super Skeleton
Recovery
𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵
Skeleton
A
DC E
B
A
DC E
BComplex
Recovery
7 / 9
Experimental Evaluation: Markov Blankets Make a Broad Range of
Inference/Learning Problems Computationally Tractable and More Precise.
●●
●●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●0.90
0.95
1.00 GSLWF
fastIAMBLWF
fdrIAMBLWF
interIAMBLWF
IAMBLWF
MBCCSPLWF
LCD
Precision
sample size
size = 200
size = 2000
alpha = 0.05
8 / 9
Experimental Evaluation: Markov Blankets Make a Broad Range of
Inference/Learning Problems Computationally Tractable and More Precise.
●●
●●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●0.90
0.95
1.00 GSLWF
fastIAMBLWF
fdrIAMBLWF
interIAMBLWF
IAMBLWF
MBCCSPLWF
LCD
Precision
sample size
size = 200
size = 2000
alpha = 0.05
● ● ● ●
●
●
0.5
0.6
0.7
0.8
0.9
1.0
GSLWF
fastIAMBLWF
fdrIAMBLWF
interIAMBLWF
IAMBLWF
MBCCSPLWF
LCD
Recall
alpha = 0.05
8 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T).
Theorem
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
5 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T).
Theorem
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
5 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
Shrink
Phase:
𝐌𝐛(𝑇) H
B
J
A
E
FC
I
M
K L
GT
D
H
B
J
A
E
FC
I
M
K L
GT
D
6 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T).
Theorem
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
5 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
Shrink
Phase:
𝐌𝐛(𝑇) H
B
J
A
E
FC
I
M
K L
GT
D
H
B
J
A
E
FC
I
M
K L
GT
D
6 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
A
DC E
B
Super Skeleton
Recovery
𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵
Skeleton
A
DC E
B
A
DC E
BComplex
Recovery
7 / 9
Markov Blankets: a Missing Concept in the Context of Chain Graph Models
H
B
J
ADE
FC
I
OM N
K L
GT H
B
J
ADE
FC
I
OM N
K L
GT𝑴𝒃(𝑇)
4 / 9
Markov Blankets in LWF Chain Graphs: Main Results
Theorem
Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional
independency T⊥⊥pV  {T, Mb(T)}|Mb(T).
Theorem
Given the Markov assumption, the faithfulness assumption, a graphical model
represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the
Markov blanket recovery algorithms Grow-Shrink, Incremental Association
Markov blanket recovery, and its variants identify all Markov blankets for each
variable.
5 / 9
MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-1 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 1-2 
𝒂𝒅𝒋(𝑇)
H
B
J
A
E
FC
I
M
K L
GT
D
Grow
Phase: 
Step 2 
𝐜𝐬𝐩(𝑇)
Shrink
Phase:
𝐌𝐛(𝑇) H
B
J
A
E
FC
I
M
K L
GT
D
H
B
J
A
E
FC
I
M
K L
GT
D
6 / 9
MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery
Observational Data
Markov Blanket
Discovery Algorithm
A
DC E
B
𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵}
𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴}
𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷}
𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴}
𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵}
A
DC E
B
Super Skeleton
Recovery
𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵
Skeleton
A
DC E
B
A
DC E
BComplex
Recovery
7 / 9
All code, data, and supplementary materials are available at:
https://majavid.github.io/structurelearning/blog/2020/uai/

More Related Content

What's hot

Ultrasound Modular Architecture
Ultrasound Modular ArchitectureUltrasound Modular Architecture
Ultrasound Modular Architecture
Jose Miguel Moreno
 
Research Inventy : International Journal of Engineering and Science is publis...
Research Inventy : International Journal of Engineering and Science is publis...Research Inventy : International Journal of Engineering and Science is publis...
Research Inventy : International Journal of Engineering and Science is publis...
researchinventy
 

What's hot (19)

Kernel for Chordal Vertex Deletion
Kernel for Chordal Vertex DeletionKernel for Chordal Vertex Deletion
Kernel for Chordal Vertex Deletion
 
Wien2k getting started
Wien2k getting startedWien2k getting started
Wien2k getting started
 
Guarding Terrains though the Lens of Parameterized Complexity
Guarding Terrains though the Lens of Parameterized ComplexityGuarding Terrains though the Lens of Parameterized Complexity
Guarding Terrains though the Lens of Parameterized Complexity
 
Mathematics Colloquium, UCSC
Mathematics Colloquium, UCSCMathematics Colloquium, UCSC
Mathematics Colloquium, UCSC
 
Graph Modification: Beyond the known Boundaries
Graph Modification: Beyond the known BoundariesGraph Modification: Beyond the known Boundaries
Graph Modification: Beyond the known Boundaries
 
Fine Grained Complexity
Fine Grained ComplexityFine Grained Complexity
Fine Grained Complexity
 
Question bank of module iv packet switching networks
Question bank of module iv packet switching networksQuestion bank of module iv packet switching networks
Question bank of module iv packet switching networks
 
Message Passing
Message PassingMessage Passing
Message Passing
 
vasp-gpu on Balena: Usage and Some Benchmarks
vasp-gpu on Balena: Usage and Some Benchmarksvasp-gpu on Balena: Usage and Some Benchmarks
vasp-gpu on Balena: Usage and Some Benchmarks
 
Fine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its VariantsFine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its Variants
 
Split Contraction: The Untold Story
Split Contraction: The Untold StorySplit Contraction: The Untold Story
Split Contraction: The Untold Story
 
1 s2.0-s2090447917300291-main
1 s2.0-s2090447917300291-main1 s2.0-s2090447917300291-main
1 s2.0-s2090447917300291-main
 
Phonons & Phonopy: Pro Tips (2015)
Phonons & Phonopy: Pro Tips (2015)Phonons & Phonopy: Pro Tips (2015)
Phonons & Phonopy: Pro Tips (2015)
 
Ultrasound Modular Architecture
Ultrasound Modular ArchitectureUltrasound Modular Architecture
Ultrasound Modular Architecture
 
Research Inventy : International Journal of Engineering and Science is publis...
Research Inventy : International Journal of Engineering and Science is publis...Research Inventy : International Journal of Engineering and Science is publis...
Research Inventy : International Journal of Engineering and Science is publis...
 
Blaha krakow 2004
Blaha krakow 2004Blaha krakow 2004
Blaha krakow 2004
 
ECE 467 Mini project 1
ECE 467 Mini project 1ECE 467 Mini project 1
ECE 467 Mini project 1
 
Density functional theory (DFT) and the concepts of the augmented-plane-wave ...
Density functional theory (DFT) and the concepts of the augmented-plane-wave ...Density functional theory (DFT) and the concepts of the augmented-plane-wave ...
Density functional theory (DFT) and the concepts of the augmented-plane-wave ...
 
Bayesian Inference and Uncertainty Quantification for Inverse Problems
Bayesian Inference and Uncertainty Quantification for Inverse ProblemsBayesian Inference and Uncertainty Quantification for Inverse Problems
Bayesian Inference and Uncertainty Quantification for Inverse Problems
 

Similar to Learning LWF Chain Graphs: A Markov Blanket Discovery Approach

System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
Cemal Ardil
 
SLAM of Multi-Robot System Considering Its Network Topology
SLAM of Multi-Robot System Considering Its Network TopologySLAM of Multi-Robot System Considering Its Network Topology
SLAM of Multi-Robot System Considering Its Network Topology
toukaigi
 
Section 4 3_the_scattering_matrix_package
Section 4 3_the_scattering_matrix_packageSection 4 3_the_scattering_matrix_package
Section 4 3_the_scattering_matrix_package
Jamal Kazazi
 
NIPS2007: structured prediction
NIPS2007: structured predictionNIPS2007: structured prediction
NIPS2007: structured prediction
zukun
 

Similar to Learning LWF Chain Graphs: A Markov Blanket Discovery Approach (20)

Algorithm_NP-Completeness Proof
Algorithm_NP-Completeness ProofAlgorithm_NP-Completeness Proof
Algorithm_NP-Completeness Proof
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 
System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
System overflow blocking-transients-for-queues-with-batch-arrivals-using-a-fa...
 
SLAM of Multi-Robot System Considering Its Network Topology
SLAM of Multi-Robot System Considering Its Network TopologySLAM of Multi-Robot System Considering Its Network Topology
SLAM of Multi-Robot System Considering Its Network Topology
 
Thesis
ThesisThesis
Thesis
 
Krunal_lbm.pptx
Krunal_lbm.pptxKrunal_lbm.pptx
Krunal_lbm.pptx
 
TMPA-2015: Implementing the MetaVCG Approach in the C-light System
TMPA-2015: Implementing the MetaVCG Approach in the C-light SystemTMPA-2015: Implementing the MetaVCG Approach in the C-light System
TMPA-2015: Implementing the MetaVCG Approach in the C-light System
 
1406
14061406
1406
 
about power system operation and control13197214.ppt
about power system operation and control13197214.pptabout power system operation and control13197214.ppt
about power system operation and control13197214.ppt
 
Generative models
Generative modelsGenerative models
Generative models
 
lecture6.pdf
lecture6.pdflecture6.pdf
lecture6.pdf
 
Report-Implementation of Quantum Gates using Verilog
Report-Implementation of Quantum Gates using VerilogReport-Implementation of Quantum Gates using Verilog
Report-Implementation of Quantum Gates using Verilog
 
Node Unique Label Cover
Node Unique Label CoverNode Unique Label Cover
Node Unique Label Cover
 
Extracting linear information from 
nonlinear large-scale structure observations
Extracting linear information from 
nonlinear large-scale structure observationsExtracting linear information from 
nonlinear large-scale structure observations
Extracting linear information from 
nonlinear large-scale structure observations
 
Section 4 3_the_scattering_matrix_package
Section 4 3_the_scattering_matrix_packageSection 4 3_the_scattering_matrix_package
Section 4 3_the_scattering_matrix_package
 
Tuning of PID, SVFB and LQ Controllers Using Genetic Algorithms
Tuning of PID, SVFB and LQ Controllers Using Genetic AlgorithmsTuning of PID, SVFB and LQ Controllers Using Genetic Algorithms
Tuning of PID, SVFB and LQ Controllers Using Genetic Algorithms
 
Paper.pdf
Paper.pdfPaper.pdf
Paper.pdf
 
Iclr2016 vaeまとめ
Iclr2016 vaeまとめIclr2016 vaeまとめ
Iclr2016 vaeまとめ
 
NIPS2007: structured prediction
NIPS2007: structured predictionNIPS2007: structured prediction
NIPS2007: structured prediction
 
Svm map reduce_slides
Svm map reduce_slidesSvm map reduce_slides
Svm map reduce_slides
 

More from Pooyan Jamshidi

Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
Pooyan Jamshidi
 
Transfer Learning for Performance Analysis of Highly-Configurable Software
Transfer Learning for Performance Analysis of Highly-Configurable SoftwareTransfer Learning for Performance Analysis of Highly-Configurable Software
Transfer Learning for Performance Analysis of Highly-Configurable Software
Pooyan Jamshidi
 
Transfer Learning for Software Performance Analysis: An Exploratory Analysis
Transfer Learning for Software Performance Analysis: An Exploratory AnalysisTransfer Learning for Software Performance Analysis: An Exploratory Analysis
Transfer Learning for Software Performance Analysis: An Exploratory Analysis
Pooyan Jamshidi
 
Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain Environments
Pooyan Jamshidi
 

More from Pooyan Jamshidi (20)

A Framework for Robust Control of Uncertainty in Self-Adaptive Software Conn...
 A Framework for Robust Control of Uncertainty in Self-Adaptive Software Conn... A Framework for Robust Control of Uncertainty in Self-Adaptive Software Conn...
A Framework for Robust Control of Uncertainty in Self-Adaptive Software Conn...
 
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
 
Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural ...
 
Transfer Learning for Performance Analysis of Machine Learning Systems
Transfer Learning for Performance Analysis of Machine Learning SystemsTransfer Learning for Performance Analysis of Machine Learning Systems
Transfer Learning for Performance Analysis of Machine Learning Systems
 
Transfer Learning for Performance Analysis of Configurable Systems: A Causal ...
Transfer Learning for Performance Analysis of Configurable Systems:A Causal ...Transfer Learning for Performance Analysis of Configurable Systems:A Causal ...
Transfer Learning for Performance Analysis of Configurable Systems: A Causal ...
 
Machine Learning meets DevOps
Machine Learning meets DevOpsMachine Learning meets DevOps
Machine Learning meets DevOps
 
Learning to Sample
Learning to SampleLearning to Sample
Learning to Sample
 
Integrated Model Discovery and Self-Adaptation of Robots
Integrated Model Discovery and Self-Adaptation of RobotsIntegrated Model Discovery and Self-Adaptation of Robots
Integrated Model Discovery and Self-Adaptation of Robots
 
Transfer Learning for Performance Analysis of Highly-Configurable Software
Transfer Learning for Performance Analysis of Highly-Configurable SoftwareTransfer Learning for Performance Analysis of Highly-Configurable Software
Transfer Learning for Performance Analysis of Highly-Configurable Software
 
Architectural Tradeoff in Learning-Based Software
Architectural Tradeoff in Learning-Based SoftwareArchitectural Tradeoff in Learning-Based Software
Architectural Tradeoff in Learning-Based Software
 
Production-Ready Machine Learning for the Software Architect
Production-Ready Machine Learning for the Software ArchitectProduction-Ready Machine Learning for the Software Architect
Production-Ready Machine Learning for the Software Architect
 
Transfer Learning for Software Performance Analysis: An Exploratory Analysis
Transfer Learning for Software Performance Analysis: An Exploratory AnalysisTransfer Learning for Software Performance Analysis: An Exploratory Analysis
Transfer Learning for Software Performance Analysis: An Exploratory Analysis
 
Architecting for Scale
Architecting for ScaleArchitecting for Scale
Architecting for Scale
 
Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain Environments
 
Sensitivity Analysis for Building Adaptive Robotic Software
Sensitivity Analysis for Building Adaptive Robotic SoftwareSensitivity Analysis for Building Adaptive Robotic Software
Sensitivity Analysis for Building Adaptive Robotic Software
 
Transfer Learning for Improving Model Predictions in Highly Configurable Soft...
Transfer Learning for Improving Model Predictions in Highly Configurable Soft...Transfer Learning for Improving Model Predictions in Highly Configurable Soft...
Transfer Learning for Improving Model Predictions in Highly Configurable Soft...
 
Transfer Learning for Improving Model Predictions in Robotic Systems
Transfer Learning for Improving Model Predictions  in Robotic SystemsTransfer Learning for Improving Model Predictions  in Robotic Systems
Transfer Learning for Improving Model Predictions in Robotic Systems
 
Machine Learning meets DevOps
Machine Learning meets DevOpsMachine Learning meets DevOps
Machine Learning meets DevOps
 
An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing S...
An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing S...An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing S...
An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing S...
 
Configuration Optimization Tool
Configuration Optimization ToolConfiguration Optimization Tool
Configuration Optimization Tool
 

Recently uploaded

1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
QucHHunhnh
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
QucHHunhnh
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
MateoGardella
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 

Recently uploaded (20)

1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 

Learning LWF Chain Graphs: A Markov Blanket Discovery Approach

  • 1. Learning LWF Chain Graphs: A Markov Blanket Discovery Approach Mohammad Ali Javidian @ali javidian Marco Valtorta @MarcoGV2 Pooyan Jamshidi @PooyanJamshidi Department of Computer Science and Engineering University of South Carolina UAI 2020 1 / 9
  • 2. LWF Chain Graphs (CGs) Chain graphs: admit both directed and undirected edges, 2 / 9
  • 3. LWF Chain Graphs (CGs) Chain graphs: admit both directed and undirected edges, there are no partially directed cycles. 2 / 9
  • 4. LWF Chain Graphs (CGs) Chain graphs: admit both directed and undirected edges, there are no partially directed cycles. A Partially directed cycle: is a sequence of n distinct vertices v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t. for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and there exists a j (1 ≤ j ≤ n) such that vj ← vj+1. 2 / 9
  • 5. LWF Chain Graphs (CGs) Chain graphs: admit both directed and undirected edges, there are no partially directed cycles. A Partially directed cycle: is a sequence of n distinct vertices v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t. for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and there exists a j (1 ≤ j ≤ n) such that vj ← vj+1. Example: 2 / 9
  • 6. LWF Chain Graphs (CGs) Chain graphs: admit both directed and undirected edges, there are no partially directed cycles. A Partially directed cycle: is a sequence of n distinct vertices v1, v2, . . . , vn(n ≥ 3), and vn+1 ≡ v1, s.t. for all i (1 ≤ i ≤ n) either vi − vi+1 or vi → vi+1, and there exists a j (1 ≤ j ≤ n) such that vj ← vj+1. Example: Chain graphs under different interpretations: LWF, AMP, MVR, ... Here, we focus on chain graphs (CGs) under the Lauritzen-Wermuth-Frydenberg (LWF) interpretation. 2 / 9
  • 7. Markov Blankets Enable Locality in Causal Structure Recovery H B J ADE FC I OM N K L GT 𝑴𝒃(𝑇) H B J ADE FC I OM N K L GT 3 / 9
  • 8. Markov Blankets Enable Locality in Causal Structure Recovery H B J ADE FC I OM N K L GT 𝑴𝒃(𝑇) H B J ADE FC I OM N K L GT 3 / 9
  • 9. Markov Blankets Enable Locality in Causal Structure Recovery H B J ADE FC I OM N K L GT 𝑴𝒃(𝑇) H B J ADE FC I OM N K L GT 𝒄𝒉(𝑇) 3 / 9
  • 10. Markov Blankets Enable Locality in Causal Structure Recovery H B J ADE FC I OM N K L GT 𝑴𝒃(𝑇) H B J ADE FC I OM N K L GT 3 / 9
  • 11. Markov Blankets Enable Locality in Causal Structure Recovery H B J ADE FC I OM N K L GT 𝑴𝒃(𝑇) H B J ADE FC I OM N K L GT Markov blankets can be used as a powerful tool in: classification, local causal discovery 3 / 9
  • 12. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9
  • 13. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 𝒑𝒂(𝑇) 4 / 9
  • 14. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 𝒄𝒉(𝑇) 4 / 9
  • 15. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 𝒏𝒆(𝑇) 4 / 9
  • 16. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 𝒄𝒔𝒑(𝑇) 4 / 9
  • 17. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9
  • 18. Markov Blankets in LWF Chain Graphs: Main Results Theorem (Characterization of Markov Blankets in LWF CGs) Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target variable T in an LWF CG probabilistically shields T from the rest of the variables. 5 / 9
  • 19. Markov Blankets in LWF Chain Graphs: Main Results Theorem (Characterization of Markov Blankets in LWF CGs) Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target variable T in an LWF CG probabilistically shields T from the rest of the variables. Theorem (Standard algorithms for Markov blanket recovery in LWF CGs) Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. 5 / 9
  • 20. Markov Blankets in LWF Chain Graphs: Main Results Theorem (Characterization of Markov Blankets in LWF CGs) Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T), i.e., the Markov blanket of the target variable T in an LWF CG probabilistically shields T from the rest of the variables. Theorem (Standard algorithms for Markov blanket recovery in LWF CGs) Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. The characterization of Markov blankets in chain graphs enables us to develop new algorithms that are specifically designed for learning Markov blankets in chain graphs. 5 / 9
  • 21. MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) 6 / 9
  • 22. MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) 6 / 9
  • 23. MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) Shrink Phase: 𝐌𝐛(𝑇) H B J A E FC I M K L GT D H B J A E FC I M K L GT D 6 / 9
  • 24. MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) Shrink Phase: 𝐌𝐛(𝑇) H B J A E FC I M K L GT D H B J A E FC I M K L GT D Such Markov blanket discovery algorithms help us to design new scalable algorithms for learning chain graphs based on local structure discovery. 6 / 9
  • 25. MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} 7 / 9
  • 26. MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} A DC E B Super Skeleton Recovery 7 / 9
  • 27. MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} A DC E B Super Skeleton Recovery 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 Skeleton A DC E B 7 / 9
  • 28. MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} A DC E B Super Skeleton Recovery 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 Skeleton A DC E B A DC E BComplex Recovery 7 / 9
  • 29. Experimental Evaluation: Markov Blankets Make a Broad Range of Inference/Learning Problems Computationally Tractable and More Precise. ●● ●● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ●0.90 0.95 1.00 GSLWF fastIAMBLWF fdrIAMBLWF interIAMBLWF IAMBLWF MBCCSPLWF LCD Precision sample size size = 200 size = 2000 alpha = 0.05 8 / 9
  • 30. Experimental Evaluation: Markov Blankets Make a Broad Range of Inference/Learning Problems Computationally Tractable and More Precise. ●● ●● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ● ●0.90 0.95 1.00 GSLWF fastIAMBLWF fdrIAMBLWF interIAMBLWF IAMBLWF MBCCSPLWF LCD Precision sample size size = 200 size = 2000 alpha = 0.05 ● ● ● ● ● ● 0.5 0.6 0.7 0.8 0.9 1.0 GSLWF fastIAMBLWF fdrIAMBLWF interIAMBLWF IAMBLWF MBCCSPLWF LCD Recall alpha = 0.05 8 / 9
  • 31. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9
  • 32. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9 Markov Blankets in LWF Chain Graphs: Main Results Theorem Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T). Theorem Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. 5 / 9
  • 33. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9 Markov Blankets in LWF Chain Graphs: Main Results Theorem Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T). Theorem Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. 5 / 9 MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) Shrink Phase: 𝐌𝐛(𝑇) H B J A E FC I M K L GT D H B J A E FC I M K L GT D 6 / 9
  • 34. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9 Markov Blankets in LWF Chain Graphs: Main Results Theorem Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T). Theorem Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. 5 / 9 MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) Shrink Phase: 𝐌𝐛(𝑇) H B J A E FC I M K L GT D H B J A E FC I M K L GT D 6 / 9 MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} A DC E B Super Skeleton Recovery 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 Skeleton A DC E B A DC E BComplex Recovery 7 / 9
  • 35. Markov Blankets: a Missing Concept in the Context of Chain Graph Models H B J ADE FC I OM N K L GT H B J ADE FC I OM N K L GT𝑴𝒃(𝑇) 4 / 9 Markov Blankets in LWF Chain Graphs: Main Results Theorem Let G = (V, E, P) be an LWF chain graph model. Then, G entails conditional independency T⊥⊥pV {T, Mb(T)}|Mb(T). Theorem Given the Markov assumption, the faithfulness assumption, a graphical model represented by an LWF CG, and i.i.d. sampling, in the large sample limit, the Markov blanket recovery algorithms Grow-Shrink, Incremental Association Markov blanket recovery, and its variants identify all Markov blankets for each variable. 5 / 9 MBC-CSP Algorithm: Markov Blanket Discovery in LWF CGs H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-1  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 1-2  𝒂𝒅𝒋(𝑇) H B J A E FC I M K L GT D Grow Phase:  Step 2  𝐜𝐬𝐩(𝑇) Shrink Phase: 𝐌𝐛(𝑇) H B J A E FC I M K L GT D H B J A E FC I M K L GT D 6 / 9 MbLWF Algorithm: Learning LWF CGs via Markov Blanket Discovery Observational Data Markov Blanket Discovery Algorithm A DC E B 𝐌𝐛 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐸 = {𝐶, 𝐵} 𝐌𝐛 𝐵 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐶 = 𝐸, 𝐴 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐵, 𝐷 = {𝐸, 𝐴} 𝐌𝐛 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐸 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐶, 𝐵 = {𝐴, 𝐷} 𝐌𝐛 𝐷 = 𝐶, 𝐸 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐴 = 𝐶, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐷, 𝐵 = {𝐸, 𝐴} 𝐌𝐛 𝐸 = 𝐷, 𝐵 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐶 = 𝐴, 𝐷 , 𝐒𝐞𝐩𝐬𝐞𝐭 𝐸, 𝐴 = {𝐶, 𝐵} A DC E B Super Skeleton Recovery 𝐒𝐞𝐩𝐬𝐞𝐭 𝐴, 𝐷 = 𝐶, 𝐵 Skeleton A DC E B A DC E BComplex Recovery 7 / 9 All code, data, and supplementary materials are available at: https://majavid.github.io/structurelearning/blog/2020/uai/