Xiaofan Wang
xfwang@sjtu.edu.cn
天地交而万物通
上下交而其志同
2011上海复杂系统论坛
Complex Networks & Control Lab, SJTU
SOCIAL LEARNING IN COMPLEX NETWORKS
What is social learning?
(Consensus on the true state)
Our recent researches
(Pinning, Similarity‐based, Chaos)
Social learning algorithms
(Bayesian + Consensus)
我的在线历程
2000 2005 2006 2010 2011
你所关注的人数
=?
你的粉丝数
围脖上所有关注的人数
=!
围脖上所有的粉丝数
汪小帆老师
90
关注
4761
粉丝
任志强汪小帆
09.7-10.3: Twitter上的2亿6千万条信息
¾ 极度不均匀:50%的信息来自0.05%的精英
¾ 并非很社会:用户更愿意发帖而不是跟帖
¾ 高度同质化:名人跟名人、媒体跟媒体
¾ 两步信息流:媒体产生的一半的信息是经
由“草根”意见领袖扩散的
¾ 不同生命期:媒体信息最短命,视频和音乐等最长命
人肉搜索为何百发百中?
Complex Networks & Control Lab, SJTU
教育医疗等却为何如此难以形成最佳共识?
围脖上的意见领袖对粉丝的影响力有多大?
热门话题、名人堂。。。
群体智慧:大众比精英更聪明!
Galton, Nature, 1907
¾ Private signals
¾ Network structure
¾ Update rules
Observing
Communicating
Updating Beliefs
Social Learning Process
1
2
3
一致性:能否形成共识?
最优性:是否最佳共识?
可控性:能否引导共识?
Complex Networks & Control Lab, SJTU
Case study: Who is singing?
State space
True state
Private signal
Likelihood function
Network structure
, ,0 ( ) 1, ( ) 1i t k i t k
k
μ θ μ θ≤ ≤ =∑
, ( *) 1i tμ θ →
Belief
Complex Networks & Control Lab, SJTU
{ }1 2, , , nθ θ θΘ = L
*θ ∈Θ
i
ts
( | ) 1i
s
l s θ =∑
( , )G V E=
观察到真实状态产生的充分信号
不存在与真实状态等价的观测状态
对真实状态的初始信念为正
Bayesian Learning:
A Single Agent Case
( )t→∞*( ) 1Ptμ θ →
1
1 1 1
1
( | ) ( )( ) ( | )
( )
t t
t t t
t
l ss
m s
θ μ θμ θ μ θ ++ + +
+
=�
Complex Networks & Control Lab, SJTU
Observationally equivalent states
Agent i is called an indiscriminative agent
*: , ( | ) ( | ) for all i i ii i il s l s s Sθ θ θ θ θ∗∃ ∈Θ ≠ = ∈
Complex Networks & Control Lab, SJTU
¾ Each agent should know the global structure of the network
¾ Each agent tries to deduce the information of every other agent
Bayesian Social Learning: Network Case
Computation burden + high complexity
Complex Networks & Control Lab, SJTU
( | ) ( )( | )
( )
l ss
m s
θ μ θμ θ =
人肉搜索有效克服了这两个困难!
Consensus Algorithm
Consensus
, 1 , ,( ) ( )
i
i t ii i t ij j t
j N
a a
Complex Networks & Control Lab, SJTU
μ θ μ θ μ θ+
∈
= + ∑ ( )
, ,( )i t j tμ θ μ θ− →( ) 0
, ( )i tμ θ → 0 , ( *) 1i tμ θ →
θ∀ ∈Θ
θ∀ ∈Θ
*θ θ∀ ≠
Social Learning = Best Consensus
Consensus Algorithm
Consensus , ,0
1( )i t j
jN
μ θ μ θ→ ∑ ()
Consensus Algorithm
Consensus
, 1 , ,( ) ( )
i
i t ii i t ij j t
j N
a a
Complex Networks & Control Lab, SJTU
μ θ μ θ μ θ+
∈
= + ∑ ( )
, ,( )i t j tμ θ μ θ− →( ) 0
, ( )i tμ θ → 0 , ( *) 1i tμ θ →
θ∀ ∈Θ
θ∀ ∈Θ
*θ θ∀ ≠
Social Learning = Best Consensus
Consensus Algorithm
Consensus , ,0
1( )i t j
jN
μ θ μ θ→ ∑ ()
Consensus Algorithm
Consensus
, 1 , ,( ) ( )
i
i t ii i t ij j t
j N
a a
Complex Networks & Control Lab, SJTU
μ θ μ θ μ θ+
∈
= + ∑ ( )
, ,( )i t j tμ θ μ θ− →( ) 0
, ( )i tμ θ → 0 , ( *) 1i tμ θ →
θ∀ ∈Θ
θ∀ ∈Θ
*θ θ∀ ≠
Social Learning = Best Consensus
Consensus Algorithm
Consensus , ,0
1( )i t j
jN
μ θ μ θ→ ∑ ()
Consensus Algorithm
Consensus
, 1 , ,( ) ( )
i
i t ii i t ij j t
j N
a a
Complex Networks & Control Lab, SJTU
μ θ μ θ μ θ+
∈
= + ∑ ( )
, ,( )i t j tμ θ μ θ− →( ) 0
, ( )i tμ θ → 0 , ( *) 1i tμ θ →
θ∀ ∈Θ
θ∀ ∈Θ
*θ θ∀ ≠
Social Learning = Best Consensus
Consensus Algorithm
Consensus , ,0
1( )i t j
jN
μ θ μ θ→ ∑ () θ∀ ∈Θ
Bayesian vs. Consensus
Consensus/
Synchronization
Bayesian
Learning
N
e
t
w
o
r
k
C
o
m
p
l
e
x
i
t
y
Rationality
Just average, but
not necessarily
true!
Demand strict!Boundedly Rational
Learning
We
se
ek
Complex Networks & Control Lab, SJTU
,
i
j t
j N
μ θ
∈
∑ ( )
, 1 ( )i tμ θ+ = θ∀ ∈Θ
, 1 1 ,( ) ( | ) ( )
i i
i t t i t i tm s l s
θ
θ μ θ+ +
∈Θ
= ∑
Bayesian Consensus
[Jadbbaie, Sandroni, and Tahbaz-saleh 2010]
1 ,
, 1
( | ) ( )
( )
i
i t i t
i
i t t
l s
m s
θ μ θ+
+
iia ij
a+
Bayesian+ Consensus
Complex Networks & Control Lab, SJTU
(e) There is no other state that is observationally equivalent to the true state
from the point of all agents in the network.
The Wisdom of Crowds
(a) The social network is strongly connected;
(b) All agents have strictly positive self-reliances;
(c) There exists an agent with positive prior belief on the true state;
*
, ( ) 1i tμ θ →
1
, 1 , ,
, 1
( | )( ) ( )
( )
i
i
i t
i t ii i t ij j ti
j Ni t t
l sa a
m s
θμ θ μ θ μ θ++
∈+
= + ∑ ( )
with probability one
Complex Networks & Control Lab, SJTU
θ∀ ∈Θ
1. Uninformed agents: those who can’t observe their
private signals;
2. Similarity-based communication: two agents
are neighbors only if they have similar beliefs;
3. Chaos in social learning with multiple true
states
Our recent works
Complex Networks & Control Lab, SJTU
Uninformed agents
Remark:
Jadbabaie’s model Consensus
l n= 0l =
Social learning with uninformed agents
Informed agents
1
, 1 , ,
, 1
( | )( ) ( ) , 1, 2, ,
( )
i
i
i t
i t ii i t ij j ti
j Ni t t
l sa a i l
m s
θμ θ μ θ μ θ++
∈+
= + =∑ L( )
, 1 , ,( ) ( ) , 1, ,
i
i t ii i t ij j t
j N
a a i l nμ θ μ θ μ θ+
∈
= + = +∑ L( )
Complex Networks & Control Lab, SJTU
(e) There is no state that is observationally equivalent to the true state from the
point of all informed agents in the network.
Social learning with uninformed agents
Suppose that
(a) The social network is strongly connected;
(b) There exists at least one informed agent and all self-reliance of informed
agents are strictly positive;
(c) There exists at least one agent with positive prior belief on the true state;
, ( *) 1i tμ θ →
Complex Networks & Control Lab, SJTU
In a power-law network with tunable exponent
2.1γ = 10γ =
Social learning with uninformed agents
Heterogeneous Homogeneous
N=1000, two states, two signals {H, T}
Prior beliefs: uniform distribution in [0,1], aii=0.5
Complex Networks & Control Lab, SJTU
Similarity Breeds Connection:
Homophily Principle in Sociology
Complex Networks & Control Lab, SJTU
{ }, ,( ) :i j t i tN t j V rμ μ= ∈ − ≤
( ) ( ) ( )( ) ( )1, 1 , ,( ), 1
|1
( )
i
i
t
i t i t j ti
j N ti i t t
p s
N t m s
θμ θ μ θ μ θ++
∈+
⎛ ⎞= +⎜ ⎟⎜ ⎟⎝ ⎠
∑
Neighbors of agent i
Update rule
Social learning with similarity-based communication
Confidence radius
Complex Networks & Control Lab, SJTU
r = 0.3 r = 0.1 r = 0.02
容忍差异才能一致
N=100, 20 discriminative agents, 80 indiscriminative agents
Two states, two signals {H, T}
Prior beliefs: random distribution in [0,1]
Originally connect
Complex Networks & Control Lab, SJTU
Differences Between
Tight and Loose Cultures:
A 33-Nation Study
If one were to order all mankind to choose
the best set of rules in the world, each group
would, after due consideration, choose its
own customs; each group regards its own as
being the best by far. ---Herodotus
Complex Networks & Control Lab, SJTU
ScMichele J. Gelfand, et al.ience27 May 2011:
Vol. 332 no. 6033 pp. 1100-1104
The Wisdom of Crowds
The larger the group, the smaller the confidence radius needed for asymptotic learning.
Complex Networks & Control Lab, SJTU
The larger the group, the smaller the proportion of discriminative agents
needed for asymptotic learning.
The Wisdom of Crowds
Discriminative agents
Indiscriminative agents
Complex Networks & Control Lab, SJTU
2
r
2
r
Feasible region
Belief update
without losing
old neighbors
Connectivity preserve strategy
Social learning with similarity-based
communication
Connectivity
preserve
Hideki Ando et al. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 15, NO. 5, 1999
r = 0.3 r = 0.1 r = 0.02
¾ Under the connectivity preserved strategy, asymptotic learning can
be achieved only if the initial network is connected
Social learning with similarity-based
communication
Complex Networks & Control Lab, SJTU
Different communities might have different underlying true states
Social learning with multiple true states
Complex Networks & Control Lab, SJTU
A connected network with two groups with two
underlying true states respectively.
Social learning with multiple true states
Signals received by
agents 6‐10 are
generated by
Signals received by
agents 1‐5 are
generated by
Three states Two signals {H,T}Prior beliefs: 1/3
Complex Networks & Control Lab, SJTU
{ }1 2 3, ,θ θ θ
2( | )l s θ 1( | )l s θ
Belief evolution of agents in group A1Belief evolution of agents in group A1 Belief evolution of agents in Group A2Belief evolution of agents in Group A2
Social learning with multiple true states
Complex Networks & Control Lab, SJTU
0.33500.33380.1481Group 2
0.19370.30190.1999Group 1
State 3State 2State 1
Social learning with multiple true states
Largest Lyapunov exponents
Complex Networks & Control Lab, SJTU
0.90930.74260.6915Group
0.92360.73200.7251Group
StateStateState
Hurst exponents H
• New adaptive social learning model
• Methods for misinformation dynamics
• Models for belief manipulation
……
What’s next?
Complex Networks & Control Lab, SJTU
Complex Networks & Control Lab, SJTU
Xiaofan Wang
Shanghai Jiao Tong University
xfwang@sjtu.edu.cn
本文档为【群体智慧--复杂网络上的最佳共识形成】,请使用软件OFFICE或WPS软件打开。作品中的文字与图均可以修改和编辑,
图片更改请在作品中右键图片并更换,文字修改请直接点击文字进行修改,也可以新增和删除文档中的内容。
该文档来自用户分享,如有侵权行为请发邮件ishare@vip.sina.com联系网站客服,我们会及时删除。
[版权声明] 本站所有资料为用户分享产生,若发现您的权利被侵害,请联系客服邮件isharekefu@iask.cn,我们尽快处理。
本作品所展示的图片、画像、字体、音乐的版权可能需版权方额外授权,请谨慎使用。
网站提供的党政主题相关内容(国旗、国徽、党徽..)目的在于配合国家政策宣传,仅限个人学习分享使用,禁止用于任何广告和商用目的。