SlideShare a Scribd company logo
1 of 16
Download to read offline
Introduction Consensus SPADE Agents Performance Conclusions
Co-Learning: Consensus-based Learning for
Multi-Agent Systems
C. Carrascosa J. Rincón M. Rebollo
VRAIN. Valencian Research Inst. for AI
Univ. Politècnica de València (Spain)
Practical Applications of Agents and Multiagent Systems
L’Aquila 2022
c b a
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Problem
Objetivo
Machine learning (ML) models can be expensive to train on a
single computer
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Federated Learning
Federated Learning
Distributed set of nodes
Train set divided into
subsets
central server averages
weights
Advantadges
Reduction of
computational load
Keeps data private
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Consensus Process in Networks
Process to share información on a
network, ruled by
xi (t+1) = xi (t)+ε
X
j∈Ni
[xj(t) − xi (t)]
Information from direct neighbors
only
0 20 40 60 80 100
EPOCH
0
0.2
0.4
0.6
0.8
1
VALUE
OLFATI CONSENSUS
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Model: FL by Consensus
Goal
To learn a global model (W , tr) of weights W for a training set tr.
n identical agents as nodes in a network. Each agent with a NN
model (Wi , tri ), being
Wi = (Wi,1, . . . , Wi,k) weight and bias matrices of node i for
component k
tri ⊆ tr fragment of the training set assigned to i.
Weights averaged in the neighborhood using consensus algorithm
(Olfati, 2007).
Wi (t + 1) = Wi (t) + ε
X
j∈Ni
[Wj(t) − Wi (t)]
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Model: FL by Consensus
The NN converge to the average values of Wi
Once adjusted, a new train epoch executes
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
SPADE Agents
This solution is implemented over SPADE architecture for
multi-agent systems
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Co-Learning Algorithm
1: while !doomsday do
2: for f ← 1, e do
3: W ← Train(f )
4: end for
5: for j ← 1, k do
6: Xi (0) ← Wj
7: for t ← 1, c do
8: Receive Xj(t) from ai neighbors
9: Xi (t + 1) ← Xi (t) + ε
P
j∈Ni
[Xj(t) − Xi (t)]
10: Send Xi (t + 1) to ai neighbors
11: end for
12: end for
13: end while
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
SPADE Behav. for FL Consensus
Finite state machine for the co-learning behaviour of the agent
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Network Topologies
6 network topologies studied to identify wich one is the best to
connect the agents
Regular 2-d Grid Triangular Grid Kleinberg's Navigable Graph
Random Geometric Graph (RGG) Delaunay Triangulation Gabriel Graph
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Degree Distribution
Degree distribution affects to the number of messages exchanged
0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0
degree
0.0
0.1
0.2
0.3
0.4
0.5
0.6
freq
2-d Grid Graph
0 1 2 3 4 5 6
degree
0.0
0.1
0.2
0.3
0.4
0.5
0.6
freq
Triangular Grid Graph
n=32
n=44
n=54
n=70
n=83
n=102
0 2 4 6 8 10 12 14
degree
0.00
0.05
0.10
0.15
0.20
0.25
0.30
freq
Navigable Graph
n=25
n=36
n=49
n=64
n=81
n=100
0 5 10 15 20 25 30
degree
0.00
0.02
0.04
0.06
0.08
0.10
0.12
0.14
freq
RGG Graph
n=25
n=36
n=49
n=64
n=81
n=100
0 5 10 15 20 25 30
degree
0.00
0.05
0.10
0.15
0.20
0.25
freq
Delaunay Graph
n=25
n=36
n=49
n=64
n=81
n=100
0 1 2 3 4 5
degree
0.0
0.1
0.2
0.3
0.4
0.5
freq
Gabriel Graph
n=25
n=36
n=49
n=64
n=81
n=100
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Global Performance
Combined with the degree, the path length its another factor that
affect to the erformance of the consensus (not to the value)
30 40 50 60 70 80 90 100
#nodes
3
4
5
6
7
8
path
length
Average Shortest Path Lengths
2d-grid
triangular
RGG
Delaunay
Gabriel
Kleinberg
30 40 50 60 70 80 90 100
#nodes
2
4
6
8
10
12
degree
Mean Degree
2d-grid
triangular
RGG
Delaunay
Gabriel
Kleinberg
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Global Performance
Total number of iterations needed for the consensus to complete
30 40 50 60 70 80 90 100
#nodes
50
100
150
200
#iterations
Consensus Performance
2d grid
triangle
RGG
Delaunay
Gabriel
Kleinberg
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Network Efficiency
How the networks behaves under random or deliberated attacks
(by degree)
0 20 40 60 80 100
#nodes removed
0.0
0.2
0.4
0.6
0.8
1.0
E
/
E
G
Network Efficiency (random)
2d grid
triangle
RGG
Delaunay
Gabriel
Kleinberg
0 20 40 60 80 100
#nodes removed
0.0
0.2
0.4
0.6
0.8
1.0
E
/
E
G
Network Efficiency (targeted)
2d grid
triangle
RGG
Delaunay
Gabriel
Kleinberg
Conclusion
RGG is the best balanced topoogy for performance and robustness
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Effect of Network Size
Accuracy and loss of the trained model after the co-learning
process
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems
Introduction Consensus SPADE Agents Performance Conclusions
Conclusions
share advances of federated learning
distributed aggregation of models
keeps privacy of datasets
RGG topologies present a good balance between performance
and robustness
@mrebollo VRAIN
Co-Learning: Consensus-based Learning for Multi-Agent Systems

More Related Content

Similar to Co-Learning: Consensus-based Learning for Multi-Agent Systems

A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsDevansh16
 
Machine Learning and Go. Go!
Machine Learning and Go. Go!Machine Learning and Go. Go!
Machine Learning and Go. Go!Diana Ortega
 
Stanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksStanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksCharles Martin
 
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N... GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...Miguel Rebollo
 
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...Jean-Claude Meteodyn
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Charles Martin
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksCharles Martin
 
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...A game theoretic approach for runtime capacity allocation in map-reduce (WACC...
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...EUBra BIGSEA
 
This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019Charles Martin
 
A short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelsA short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelstuxette
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)byteLAKE
 
Keynote at IWLS 2017
Keynote at IWLS 2017Keynote at IWLS 2017
Keynote at IWLS 2017Manish Pandey
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfPolytechnique Montréal
 
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...Rafael Nogueras
 
High-Dimensional Network Estimation using ECL
High-Dimensional Network Estimation using ECLHigh-Dimensional Network Estimation using ECL
High-Dimensional Network Estimation using ECLHPCC Systems
 
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free Networks
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free NetworksSelf-Balancing Multimemetic Algorithms in Dynamic Scale-Free Networks
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free NetworksRafael Nogueras
 
SVD and the Netflix Dataset
SVD and the Netflix DatasetSVD and the Netflix Dataset
SVD and the Netflix DatasetBen Mabey
 
Colfax-Winograd-Summary _final (1)
Colfax-Winograd-Summary _final (1)Colfax-Winograd-Summary _final (1)
Colfax-Winograd-Summary _final (1)Sangamesh Ragate
 

Similar to Co-Learning: Consensus-based Learning for Multi-Agent Systems (20)

A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representations
 
Machine Learning and Go. Go!
Machine Learning and Go. Go!Machine Learning and Go. Go!
Machine Learning and Go. Go!
 
Stanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksStanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning Works
 
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N... GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
GTG-CoL: A Decentralized Federated Learning Based on Consensus for Dynamic N...
 
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...
Wind meteodyn WT cfd micro scale modeling combined statistical learning for s...
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks
 
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...A game theoretic approach for runtime capacity allocation in map-reduce (WACC...
A game theoretic approach for runtime capacity allocation in map-reduce (WACC...
 
This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019
 
Mlab i
Mlab iMlab i
Mlab i
 
A short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction modelsA short and naive introduction to using network in prediction models
A short and naive introduction to using network in prediction models
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
 
Keynote at IWLS 2017
Keynote at IWLS 2017Keynote at IWLS 2017
Keynote at IWLS 2017
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdf
 
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...
A Performance Analysis of Self-* Evolutionary Algorithms on Networks with Cor...
 
High-Dimensional Network Estimation using ECL
High-Dimensional Network Estimation using ECLHigh-Dimensional Network Estimation using ECL
High-Dimensional Network Estimation using ECL
 
PointNet
PointNetPointNet
PointNet
 
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free Networks
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free NetworksSelf-Balancing Multimemetic Algorithms in Dynamic Scale-Free Networks
Self-Balancing Multimemetic Algorithms in Dynamic Scale-Free Networks
 
SVD and the Netflix Dataset
SVD and the Netflix DatasetSVD and the Netflix Dataset
SVD and the Netflix Dataset
 
Colfax-Winograd-Summary _final (1)
Colfax-Winograd-Summary _final (1)Colfax-Winograd-Summary _final (1)
Colfax-Winograd-Summary _final (1)
 

More from Miguel Rebollo

Análisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de ClarkesworldAnálisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de ClarkesworldMiguel Rebollo
 
Y sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejasY sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejasMiguel Rebollo
 
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluaciónExámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluaciónMiguel Rebollo
 
Gamification. Key Concepts
Gamification. Key ConceptsGamification. Key Concepts
Gamification. Key ConceptsMiguel Rebollo
 
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing AppsUsing Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing AppsMiguel Rebollo
 
Distributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for AgreementsDistributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for AgreementsMiguel Rebollo
 
Detección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redesDetección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redesMiguel Rebollo
 
La hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacionalLa hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacionalMiguel Rebollo
 
Procesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en redProcesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en redMiguel Rebollo
 
desarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmediadesarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmediaMiguel Rebollo
 
Distributed Group Analytical Hierarchical Process by Consensus
 Distributed Group Analytical Hierarchical Process by Consensus Distributed Group Analytical Hierarchical Process by Consensus
Distributed Group Analytical Hierarchical Process by ConsensusMiguel Rebollo
 
Análisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes socialesAnálisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes socialesMiguel Rebollo
 
Análisis de datos en redes sociales
Análisis de datos en redes socialesAnálisis de datos en redes sociales
Análisis de datos en redes socialesMiguel Rebollo
 
The multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURFThe multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURFMiguel Rebollo
 
Narrativa transmedia en el aula
Narrativa transmedia en el aulaNarrativa transmedia en el aula
Narrativa transmedia en el aulaMiguel Rebollo
 
Using geo-tagged sentiment to better understand social interactions
 Using geo-tagged sentiment to better understand social interactions Using geo-tagged sentiment to better understand social interactions
Using geo-tagged sentiment to better understand social interactionsMiguel Rebollo
 
Transport Network Analysis for Smart Open Fleets
Transport Network Analysis for Smart Open FleetsTransport Network Analysis for Smart Open Fleets
Transport Network Analysis for Smart Open FleetsMiguel Rebollo
 
Análisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMMAnálisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMMMiguel Rebollo
 
La (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondoLa (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondoMiguel Rebollo
 
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activityU-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activityMiguel Rebollo
 

More from Miguel Rebollo (20)

Análisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de ClarkesworldAnálisis de la red de autores de ciencia ficción de Clarkesworld
Análisis de la red de autores de ciencia ficción de Clarkesworld
 
Y sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejasY sin embargo... se mueve. Dinámica de las redes complejas
Y sin embargo... se mueve. Dinámica de las redes complejas
 
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluaciónExámenes en grupo y pruebas de corrección como alternativas a la evaluación
Exámenes en grupo y pruebas de corrección como alternativas a la evaluación
 
Gamification. Key Concepts
Gamification. Key ConceptsGamification. Key Concepts
Gamification. Key Concepts
 
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing AppsUsing Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
Using Distributed Risk Maps by Consensus as a Complement to Contact Tracing Apps
 
Distributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for AgreementsDistributed Ledger and Robust Consensus for Agreements
Distributed Ledger and Robust Consensus for Agreements
 
Detección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redesDetección de nodos tramposos en procesos de consenso en redes
Detección de nodos tramposos en procesos de consenso en redes
 
La hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacionalLa hora del código: ApS para fomentar el pensamiento computacional
La hora del código: ApS para fomentar el pensamiento computacional
 
Procesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en redProcesos de enseñanza-aprendizaje en red
Procesos de enseñanza-aprendizaje en red
 
desarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmediadesarrollo de competencias a través de narrativas transmedia
desarrollo de competencias a través de narrativas transmedia
 
Distributed Group Analytical Hierarchical Process by Consensus
 Distributed Group Analytical Hierarchical Process by Consensus Distributed Group Analytical Hierarchical Process by Consensus
Distributed Group Analytical Hierarchical Process by Consensus
 
Análisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes socialesAnálisis de ciudades a través de su actividad en redes sociales
Análisis de ciudades a través de su actividad en redes sociales
 
Análisis de datos en redes sociales
Análisis de datos en redes socialesAnálisis de datos en redes sociales
Análisis de datos en redes sociales
 
The multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURFThe multigent Layer for CALMeD SURF
The multigent Layer for CALMeD SURF
 
Narrativa transmedia en el aula
Narrativa transmedia en el aulaNarrativa transmedia en el aula
Narrativa transmedia en el aula
 
Using geo-tagged sentiment to better understand social interactions
 Using geo-tagged sentiment to better understand social interactions Using geo-tagged sentiment to better understand social interactions
Using geo-tagged sentiment to better understand social interactions
 
Transport Network Analysis for Smart Open Fleets
Transport Network Analysis for Smart Open FleetsTransport Network Analysis for Smart Open Fleets
Transport Network Analysis for Smart Open Fleets
 
Análisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMMAnálisis de sentimientos en Twitter mediante HMM
Análisis de sentimientos en Twitter mediante HMM
 
La (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondoLa (poca) soledad del corredor de fondo
La (poca) soledad del corredor de fondo
 
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activityU-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
U-Tool: A Urban-Toolkit for enhancing city maps through citizens’ activity
 

Recently uploaded

Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 

Recently uploaded (20)

Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 

Co-Learning: Consensus-based Learning for Multi-Agent Systems

  • 1. Introduction Consensus SPADE Agents Performance Conclusions Co-Learning: Consensus-based Learning for Multi-Agent Systems C. Carrascosa J. Rincón M. Rebollo VRAIN. Valencian Research Inst. for AI Univ. Politècnica de València (Spain) Practical Applications of Agents and Multiagent Systems L’Aquila 2022 c b a @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 2. Introduction Consensus SPADE Agents Performance Conclusions Problem Objetivo Machine learning (ML) models can be expensive to train on a single computer @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 3. Introduction Consensus SPADE Agents Performance Conclusions Federated Learning Federated Learning Distributed set of nodes Train set divided into subsets central server averages weights Advantadges Reduction of computational load Keeps data private @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 4. Introduction Consensus SPADE Agents Performance Conclusions Consensus Process in Networks Process to share información on a network, ruled by xi (t+1) = xi (t)+ε X j∈Ni [xj(t) − xi (t)] Information from direct neighbors only 0 20 40 60 80 100 EPOCH 0 0.2 0.4 0.6 0.8 1 VALUE OLFATI CONSENSUS @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 5. Introduction Consensus SPADE Agents Performance Conclusions Model: FL by Consensus Goal To learn a global model (W , tr) of weights W for a training set tr. n identical agents as nodes in a network. Each agent with a NN model (Wi , tri ), being Wi = (Wi,1, . . . , Wi,k) weight and bias matrices of node i for component k tri ⊆ tr fragment of the training set assigned to i. Weights averaged in the neighborhood using consensus algorithm (Olfati, 2007). Wi (t + 1) = Wi (t) + ε X j∈Ni [Wj(t) − Wi (t)] @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 6. Introduction Consensus SPADE Agents Performance Conclusions Model: FL by Consensus The NN converge to the average values of Wi Once adjusted, a new train epoch executes @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 7. Introduction Consensus SPADE Agents Performance Conclusions SPADE Agents This solution is implemented over SPADE architecture for multi-agent systems @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 8. Introduction Consensus SPADE Agents Performance Conclusions Co-Learning Algorithm 1: while !doomsday do 2: for f ← 1, e do 3: W ← Train(f ) 4: end for 5: for j ← 1, k do 6: Xi (0) ← Wj 7: for t ← 1, c do 8: Receive Xj(t) from ai neighbors 9: Xi (t + 1) ← Xi (t) + ε P j∈Ni [Xj(t) − Xi (t)] 10: Send Xi (t + 1) to ai neighbors 11: end for 12: end for 13: end while @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 9. Introduction Consensus SPADE Agents Performance Conclusions SPADE Behav. for FL Consensus Finite state machine for the co-learning behaviour of the agent @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 10. Introduction Consensus SPADE Agents Performance Conclusions Network Topologies 6 network topologies studied to identify wich one is the best to connect the agents Regular 2-d Grid Triangular Grid Kleinberg's Navigable Graph Random Geometric Graph (RGG) Delaunay Triangulation Gabriel Graph @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 11. Introduction Consensus SPADE Agents Performance Conclusions Degree Distribution Degree distribution affects to the number of messages exchanged 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0 degree 0.0 0.1 0.2 0.3 0.4 0.5 0.6 freq 2-d Grid Graph 0 1 2 3 4 5 6 degree 0.0 0.1 0.2 0.3 0.4 0.5 0.6 freq Triangular Grid Graph n=32 n=44 n=54 n=70 n=83 n=102 0 2 4 6 8 10 12 14 degree 0.00 0.05 0.10 0.15 0.20 0.25 0.30 freq Navigable Graph n=25 n=36 n=49 n=64 n=81 n=100 0 5 10 15 20 25 30 degree 0.00 0.02 0.04 0.06 0.08 0.10 0.12 0.14 freq RGG Graph n=25 n=36 n=49 n=64 n=81 n=100 0 5 10 15 20 25 30 degree 0.00 0.05 0.10 0.15 0.20 0.25 freq Delaunay Graph n=25 n=36 n=49 n=64 n=81 n=100 0 1 2 3 4 5 degree 0.0 0.1 0.2 0.3 0.4 0.5 freq Gabriel Graph n=25 n=36 n=49 n=64 n=81 n=100 @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 12. Introduction Consensus SPADE Agents Performance Conclusions Global Performance Combined with the degree, the path length its another factor that affect to the erformance of the consensus (not to the value) 30 40 50 60 70 80 90 100 #nodes 3 4 5 6 7 8 path length Average Shortest Path Lengths 2d-grid triangular RGG Delaunay Gabriel Kleinberg 30 40 50 60 70 80 90 100 #nodes 2 4 6 8 10 12 degree Mean Degree 2d-grid triangular RGG Delaunay Gabriel Kleinberg @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 13. Introduction Consensus SPADE Agents Performance Conclusions Global Performance Total number of iterations needed for the consensus to complete 30 40 50 60 70 80 90 100 #nodes 50 100 150 200 #iterations Consensus Performance 2d grid triangle RGG Delaunay Gabriel Kleinberg @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 14. Introduction Consensus SPADE Agents Performance Conclusions Network Efficiency How the networks behaves under random or deliberated attacks (by degree) 0 20 40 60 80 100 #nodes removed 0.0 0.2 0.4 0.6 0.8 1.0 E / E G Network Efficiency (random) 2d grid triangle RGG Delaunay Gabriel Kleinberg 0 20 40 60 80 100 #nodes removed 0.0 0.2 0.4 0.6 0.8 1.0 E / E G Network Efficiency (targeted) 2d grid triangle RGG Delaunay Gabriel Kleinberg Conclusion RGG is the best balanced topoogy for performance and robustness @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 15. Introduction Consensus SPADE Agents Performance Conclusions Effect of Network Size Accuracy and loss of the trained model after the co-learning process @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems
  • 16. Introduction Consensus SPADE Agents Performance Conclusions Conclusions share advances of federated learning distributed aggregation of models keeps privacy of datasets RGG topologies present a good balance between performance and robustness @mrebollo VRAIN Co-Learning: Consensus-based Learning for Multi-Agent Systems