SlideShare a Scribd company logo
Kundjanasith Thonglek1
, Keichi Takahashi1
, Kohei Ichikawa1
,
Chawanat Nakasan2
, Hajimu Iida1
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
1
Nara Institute of Science and Technology, Nara, Japan
2
Kanazawa University, Ishikawa, Japan
Federated Learning
of Neural Network Models
with Heterogeneous Structures
Edge intelligence
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Cloud-based AI Edge-based AI
AI
?
➢ Gather data from edge devices
➢ Update the model frequently
➢ Longer response time
➢ Lack of data privacy
DATA
DATA
Input Data
Input Data
Inference Result
Inference Result
AI
DATA
DATA
AI
AI
Input Data
Input Data
Inference Result
Inference Result
Pros
Cons
➢ Shorter response time
➢ Better data privacy
➢ Cannot update the model from
data collected at the edge
Pros
Cons
2
Federated learning
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Global
Model
Ref: J. Konecný, H. Brendan McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, D. Bacon, “Federated Learning: Strategies for
Improving Communication Efficiency”, NIPS Workshop on Private Multi-Party Machine Learning, 2016.
Federated Learning Algorithm
Model
Aggregation
3
Require the models with homogeneous structures
DATA
DATA
Local
Model
Local
Model
Updated parameters
Heterogeneity of edge devices
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Network
Bandwidth
Power
Consumption
Storage
Capacity
Computing
Resources
TPU Tensor
Processing Unit
Graphics
Processing Unit
GPU
4
Federated Learning
Algorithm
Federated learning for heterogeneous models
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
DATA
DATA
MobileNet
[17.02 MB.]
VGG16
[553.43 MB.]
Proposed
Method
5
Updated parameters of MobileNet
Updated parameters of VGG16
Centralized Server
Proposed method
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Proposed Method
Weighted Average
Ensembling
6
DATA
DATA
DATA
DATA
Model
1
Model
1
Model
2
Model
2
Model
1
Model
2
Federated Learning Algorithm
[FedAVG]
Federated Learning Algorithm
[FedAVG]
Weighted average ensembling
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 7
Let y be the final output vector
Let x be the input data
Let N be the number of models
Let mi
(x) be the prediction of x using the i-th model
Let 𝛼i
be the weight vector for the i-th model
To be determined by applying optimization algorithms
Optimization algorithms
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
6 Tree Parzen Estimator
TPE
Ref: H. Frank, H. Holger, and L. B. Kevin, “Sequential model-based optimization for general algorithm
configuration,” International Conference on Learning and Intelligent Optimization, Jan. 2011
4 Bayesian Search
BS
Ref: A. Garcia, E. Campos, and C. Li, “Distributed on-line Bayesian search,” International Conference on
Collaborative Computing: Networking, Applications and Worksharing, Dec. 2005
2 Random Search
RS
Ref: Y. Shang and J. Chu, “A method based on random search algorithm for unequal circle packing problem,”
International Conference on Information Science and Cloud Computing Companion,, Dec. 2013
3
Particle Swarm Optimization
PSO
Ref: M. Kirschenbaum and D. W. Palmer, “Perceptualization of particle swarm optimization,”
in Proceedings of the Swarm/Human Blended Intelligence Workshop, Sep. 2015
1
Grid Search
GS
Ref: F. Xue, D. Wei, Z. Wang, T. Li, Y. Hu, and H. Huang, “Grid searching method in spherical coordinate for PD
location in a substation,” International Conference on Condition Monitoring and Diagnosis, Sep. 2018
5
Sequential Model-based Algorithm Configuration
SMAC
Ref: M. Zhao and J. Li, “Tuning the hyper-parameters of CMA-ES with tree-structured Parzen estimators,”
International Conference on Advanced Computational Intelligence, Mar. 2018
5
8
Experimental setup
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Setup
A B C
Total # of devices 1,200 1,200 1,200
# of models 2
1. MobileNet
2. DenseNet169
3
1. MobileNet
2. DenseNet169
3. ResNet50
4
1. MobileNet
2. DenseNet169
3. ResNet50
4. VGG16
# of devices per model 600 400 300
# of images per model 24,000 16,000 12,000
9
Model specification
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 10
Datasets
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Name # of images # of output classes
CIFAR-10[1]
70,000 10
CIFAR-100[2]
70,000 100
ImageNet[3]
100,000 1,000
R-Cellular[4]
73,000 1,108
References:
[1] https://www.cs.toronto.edu/~kriz/cifar.html#CIFAR-10
[2] https://www.cs.toronto.edu/~kriz/cifar.html#CIFAR-100
[3] http://image-net.org/download
[4] https://www.kaggle.com/c/recursion-cellular-image-classification
11
Optimized weights
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Experimental Setup
➢ Setup C
Dataset
➢ CIFAR-10
Optimization
➢ TPE
12
Improvement of accuracy
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Experimental Setup A & R-Cellular Dataset
63.19% (before optimizing the weights)
13
Accuracy & Runtime
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
Experimental Setup A & R-Cellular Dataset
14
Conclusion
IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020
➢ We proposed a novel method to ensemble neural network models
with heterogeneous structures for federated learning
➢ We compared six optimization algorithms to tune the weights for
the output classes of each model and found that TPE was able to
achieve the highest accuracy
We will investigate other parameter optimization methods and
federated learning algorithms
15
Q&A
Thank you for your attention
Email: thonglek.kundjanasith.ti7@is.naist.jp

More Related Content

What's hot

Lifi (presentation)
Lifi (presentation)Lifi (presentation)
Lifi (presentation)
Aman Durrani
 
Intro to LLMs
Intro to LLMsIntro to LLMs
Intro to LLMs
Loic Merckel
 
Cisco Internet of Things
Cisco Internet of ThingsCisco Internet of Things
Cisco Internet of Things
Panduit
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
Data Con LA
 
Cyber-Physical Systems
Cyber-Physical SystemsCyber-Physical Systems
Cyber-Physical Systems
Sinem Coleri Ergen
 
Quantum Cryptography presentation
Quantum Cryptography presentationQuantum Cryptography presentation
Quantum Cryptography presentation
Kalluri Madhuri
 
IoT Connectivity
IoT Connectivity IoT Connectivity
IoT Connectivity
Hitesh Mohapatra
 
Cyber Physical System: Architecture, Applications and Research Challenges
Cyber Physical System: Architecture, Applicationsand Research ChallengesCyber Physical System: Architecture, Applicationsand Research Challenges
Cyber Physical System: Architecture, Applications and Research Challenges
Syed Hassan Ahmed
 
Quantum Computing
Quantum ComputingQuantum Computing
Quantum Computing
Keshav
 
Edge Computing
Edge ComputingEdge Computing
Edge Computing
Chetan Kumar S
 
An Introduction to Generative AI
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AI
Cori Faklaris
 
Context-Aware Computing
Context-Aware ComputingContext-Aware Computing
Context-Aware Computing
logus2k
 
Machine Learning in IOT
Machine Learning in IOTMachine Learning in IOT
Machine Learning in IOT
ArikumarKS2
 
Quantum Information Technology
Quantum Information TechnologyQuantum Information Technology
Quantum Information Technology
Fenny Thakrar
 
Quantum neural network
Quantum neural networkQuantum neural network
Quantum neural network
surat murthy
 
Edge Computing.pptx
Edge Computing.pptxEdge Computing.pptx
Edge Computing.pptx
PriyaMaurya52
 
The Future is in Responsible Generative AI
The Future is in Responsible Generative AIThe Future is in Responsible Generative AI
The Future is in Responsible Generative AI
Saeed Al Dhaheri
 
Quantum computers
Quantum computersQuantum computers
Quantum computers
Nolesh_Warke
 
History of AI
History of AIHistory of AI
History of AI
Sanjay Kumar
 
Edge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to YouEdge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to You
Megan O'Keefe
 

What's hot (20)

Lifi (presentation)
Lifi (presentation)Lifi (presentation)
Lifi (presentation)
 
Intro to LLMs
Intro to LLMsIntro to LLMs
Intro to LLMs
 
Cisco Internet of Things
Cisco Internet of ThingsCisco Internet of Things
Cisco Internet of Things
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
 
Cyber-Physical Systems
Cyber-Physical SystemsCyber-Physical Systems
Cyber-Physical Systems
 
Quantum Cryptography presentation
Quantum Cryptography presentationQuantum Cryptography presentation
Quantum Cryptography presentation
 
IoT Connectivity
IoT Connectivity IoT Connectivity
IoT Connectivity
 
Cyber Physical System: Architecture, Applications and Research Challenges
Cyber Physical System: Architecture, Applicationsand Research ChallengesCyber Physical System: Architecture, Applicationsand Research Challenges
Cyber Physical System: Architecture, Applications and Research Challenges
 
Quantum Computing
Quantum ComputingQuantum Computing
Quantum Computing
 
Edge Computing
Edge ComputingEdge Computing
Edge Computing
 
An Introduction to Generative AI
An Introduction  to Generative AIAn Introduction  to Generative AI
An Introduction to Generative AI
 
Context-Aware Computing
Context-Aware ComputingContext-Aware Computing
Context-Aware Computing
 
Machine Learning in IOT
Machine Learning in IOTMachine Learning in IOT
Machine Learning in IOT
 
Quantum Information Technology
Quantum Information TechnologyQuantum Information Technology
Quantum Information Technology
 
Quantum neural network
Quantum neural networkQuantum neural network
Quantum neural network
 
Edge Computing.pptx
Edge Computing.pptxEdge Computing.pptx
Edge Computing.pptx
 
The Future is in Responsible Generative AI
The Future is in Responsible Generative AIThe Future is in Responsible Generative AI
The Future is in Responsible Generative AI
 
Quantum computers
Quantum computersQuantum computers
Quantum computers
 
History of AI
History of AIHistory of AI
History of AI
 
Edge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to YouEdge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to You
 

Similar to Federated Learning of Neural Network Models with Heterogeneous Structures.pdf

Information Technology in Industry(ITII) - November Issue 2018
Information Technology in Industry(ITII) - November Issue 2018Information Technology in Industry(ITII) - November Issue 2018
Information Technology in Industry(ITII) - November Issue 2018
ITIIIndustries
 
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdfMay_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
IJCNCJournal
 
4th International Conference on NLP & Big Data (NLPD 2023)
4th International Conference on NLP & Big Data (NLPD 2023)4th International Conference on NLP & Big Data (NLPD 2023)
4th International Conference on NLP & Big Data (NLPD 2023)
aciijournal
 
Publication list
Publication listPublication list
Publication list
drcgdethe
 
DEF CON 27 - BRENT STONE - reverse enginerring 17 cars
DEF CON 27 - BRENT STONE - reverse enginerring 17 carsDEF CON 27 - BRENT STONE - reverse enginerring 17 cars
DEF CON 27 - BRENT STONE - reverse enginerring 17 cars
Felipe Prado
 
Introduction and e research time line review
Introduction and e research time line reviewIntroduction and e research time line review
Introduction and e research time line review
ShishirAryal1
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
Paolo Missier
 
Iciic2010 114
Iciic2010 114Iciic2010 114
Iciic2010 114
hanums1
 
Mythri_Thippareddy_Resume
Mythri_Thippareddy_ResumeMythri_Thippareddy_Resume
Mythri_Thippareddy_Resume
Mythri Thippareddy
 
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
ijistjournal
 
Large scale gpu cluster for ai
Large scale gpu cluster for aiLarge scale gpu cluster for ai
Large scale gpu cluster for ai
Kyunam Cho
 
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
sebastianku31
 
Official resume titash_mandal_
Official resume titash_mandal_Official resume titash_mandal_
Official resume titash_mandal_
Titash Mandal
 
June 2022: Top 10 Read Articles in Signal & Image Processing
June 2022: Top 10 Read Articles in Signal & Image   ProcessingJune 2022: Top 10 Read Articles in Signal & Image   Processing
June 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
Resume
ResumeResume
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
IJNSA Journal
 
July 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image ProcessingJuly 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
Pramod2016 Mumbai
Pramod2016 MumbaiPramod2016 Mumbai
Pramod2016 Mumbai
Pramod K B Rangaiah
 
Arpan pal icdcn
Arpan pal icdcnArpan pal icdcn
Arpan pal icdcn
Arpan Pal
 
Performance evaluation of Wearable Computing Frameworks
Performance evaluation of Wearable Computing FrameworksPerformance evaluation of Wearable Computing Frameworks
Performance evaluation of Wearable Computing Frameworks
Michelle Guerreiro C Silva
 

Similar to Federated Learning of Neural Network Models with Heterogeneous Structures.pdf (20)

Information Technology in Industry(ITII) - November Issue 2018
Information Technology in Industry(ITII) - November Issue 2018Information Technology in Industry(ITII) - November Issue 2018
Information Technology in Industry(ITII) - November Issue 2018
 
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdfMay_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdf
 
4th International Conference on NLP & Big Data (NLPD 2023)
4th International Conference on NLP & Big Data (NLPD 2023)4th International Conference on NLP & Big Data (NLPD 2023)
4th International Conference on NLP & Big Data (NLPD 2023)
 
Publication list
Publication listPublication list
Publication list
 
DEF CON 27 - BRENT STONE - reverse enginerring 17 cars
DEF CON 27 - BRENT STONE - reverse enginerring 17 carsDEF CON 27 - BRENT STONE - reverse enginerring 17 cars
DEF CON 27 - BRENT STONE - reverse enginerring 17 cars
 
Introduction and e research time line review
Introduction and e research time line reviewIntroduction and e research time line review
Introduction and e research time line review
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
 
Iciic2010 114
Iciic2010 114Iciic2010 114
Iciic2010 114
 
Mythri_Thippareddy_Resume
Mythri_Thippareddy_ResumeMythri_Thippareddy_Resume
Mythri_Thippareddy_Resume
 
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
 
Large scale gpu cluster for ai
Large scale gpu cluster for aiLarge scale gpu cluster for ai
Large scale gpu cluster for ai
 
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
May 2024: Top 10 Read Articles in Software Engineering & Applications Interna...
 
Official resume titash_mandal_
Official resume titash_mandal_Official resume titash_mandal_
Official resume titash_mandal_
 
June 2022: Top 10 Read Articles in Signal & Image Processing
June 2022: Top 10 Read Articles in Signal & Image   ProcessingJune 2022: Top 10 Read Articles in Signal & Image   Processing
June 2022: Top 10 Read Articles in Signal & Image Processing
 
Resume
ResumeResume
Resume
 
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
Call for Papers - 2nd International Conference on NLP, Data Mining and Machin...
 
July 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image ProcessingJuly 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image Processing
 
Pramod2016 Mumbai
Pramod2016 MumbaiPramod2016 Mumbai
Pramod2016 Mumbai
 
Arpan pal icdcn
Arpan pal icdcnArpan pal icdcn
Arpan pal icdcn
 
Performance evaluation of Wearable Computing Frameworks
Performance evaluation of Wearable Computing FrameworksPerformance evaluation of Wearable Computing Frameworks
Performance evaluation of Wearable Computing Frameworks
 

More from Kundjanasith Thonglek

Sparse Communication for Federated Learning
Sparse Communication for Federated LearningSparse Communication for Federated Learning
Sparse Communication for Federated Learning
Kundjanasith Thonglek
 
Improving Resource Availability in Data Center using Deep Learning.pdf
Improving Resource Availability in Data Center using Deep Learning.pdfImproving Resource Availability in Data Center using Deep Learning.pdf
Improving Resource Availability in Data Center using Deep Learning.pdf
Kundjanasith Thonglek
 
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
Kundjanasith Thonglek
 
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdfAbnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
Kundjanasith Thonglek
 
Retraining Quantized Neural Network Models with Unlabeled Data.pdf
Retraining Quantized Neural Network Models with Unlabeled Data.pdfRetraining Quantized Neural Network Models with Unlabeled Data.pdf
Retraining Quantized Neural Network Models with Unlabeled Data.pdf
Kundjanasith Thonglek
 
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
Kundjanasith Thonglek
 
Intelligent Vehicle Accident Analysis System.pdf
Intelligent Vehicle Accident Analysis System.pdfIntelligent Vehicle Accident Analysis System.pdf
Intelligent Vehicle Accident Analysis System.pdf
Kundjanasith Thonglek
 
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdfAuto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
Kundjanasith Thonglek
 

More from Kundjanasith Thonglek (8)

Sparse Communication for Federated Learning
Sparse Communication for Federated LearningSparse Communication for Federated Learning
Sparse Communication for Federated Learning
 
Improving Resource Availability in Data Center using Deep Learning.pdf
Improving Resource Availability in Data Center using Deep Learning.pdfImproving Resource Availability in Data Center using Deep Learning.pdf
Improving Resource Availability in Data Center using Deep Learning.pdf
 
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
Enhancing the Prediction Accuracy of Solar Power Generation using a Generativ...
 
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdfAbnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks.pdf
 
Retraining Quantized Neural Network Models with Unlabeled Data.pdf
Retraining Quantized Neural Network Models with Unlabeled Data.pdfRetraining Quantized Neural Network Models with Unlabeled Data.pdf
Retraining Quantized Neural Network Models with Unlabeled Data.pdf
 
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
Improving Resource Utilization in Data Centers using an LSTM-based Prediction...
 
Intelligent Vehicle Accident Analysis System.pdf
Intelligent Vehicle Accident Analysis System.pdfIntelligent Vehicle Accident Analysis System.pdf
Intelligent Vehicle Accident Analysis System.pdf
 
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdfAuto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdf
 

Recently uploaded

Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
shyamraj55
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
saastr
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Wask
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
Pixlogix Infotech
 
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptxOcean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
SitimaJohn
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
kumardaparthi1024
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
HarisZaheer8
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
GDSC PJATK
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
Zilliz
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
Zilliz
 
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdfNunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
flufftailshop
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
alexjohnson7307
 

Recently uploaded (20)

Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
 
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptxOcean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
 
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdfNunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
 

Federated Learning of Neural Network Models with Heterogeneous Structures.pdf

  • 1. Kundjanasith Thonglek1 , Keichi Takahashi1 , Kohei Ichikawa1 , Chawanat Nakasan2 , Hajimu Iida1 IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 1 Nara Institute of Science and Technology, Nara, Japan 2 Kanazawa University, Ishikawa, Japan Federated Learning of Neural Network Models with Heterogeneous Structures
  • 2. Edge intelligence IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Cloud-based AI Edge-based AI AI ? ➢ Gather data from edge devices ➢ Update the model frequently ➢ Longer response time ➢ Lack of data privacy DATA DATA Input Data Input Data Inference Result Inference Result AI DATA DATA AI AI Input Data Input Data Inference Result Inference Result Pros Cons ➢ Shorter response time ➢ Better data privacy ➢ Cannot update the model from data collected at the edge Pros Cons 2
  • 3. Federated learning IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Global Model Ref: J. Konecný, H. Brendan McMahan, F. X. Yu, P. Richtárik, A. T. Suresh, D. Bacon, “Federated Learning: Strategies for Improving Communication Efficiency”, NIPS Workshop on Private Multi-Party Machine Learning, 2016. Federated Learning Algorithm Model Aggregation 3 Require the models with homogeneous structures DATA DATA Local Model Local Model Updated parameters
  • 4. Heterogeneity of edge devices IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Network Bandwidth Power Consumption Storage Capacity Computing Resources TPU Tensor Processing Unit Graphics Processing Unit GPU 4
  • 5. Federated Learning Algorithm Federated learning for heterogeneous models IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 DATA DATA MobileNet [17.02 MB.] VGG16 [553.43 MB.] Proposed Method 5 Updated parameters of MobileNet Updated parameters of VGG16
  • 6. Centralized Server Proposed method IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Proposed Method Weighted Average Ensembling 6 DATA DATA DATA DATA Model 1 Model 1 Model 2 Model 2 Model 1 Model 2 Federated Learning Algorithm [FedAVG] Federated Learning Algorithm [FedAVG]
  • 7. Weighted average ensembling IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 7 Let y be the final output vector Let x be the input data Let N be the number of models Let mi (x) be the prediction of x using the i-th model Let 𝛼i be the weight vector for the i-th model To be determined by applying optimization algorithms
  • 8. Optimization algorithms IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 6 Tree Parzen Estimator TPE Ref: H. Frank, H. Holger, and L. B. Kevin, “Sequential model-based optimization for general algorithm configuration,” International Conference on Learning and Intelligent Optimization, Jan. 2011 4 Bayesian Search BS Ref: A. Garcia, E. Campos, and C. Li, “Distributed on-line Bayesian search,” International Conference on Collaborative Computing: Networking, Applications and Worksharing, Dec. 2005 2 Random Search RS Ref: Y. Shang and J. Chu, “A method based on random search algorithm for unequal circle packing problem,” International Conference on Information Science and Cloud Computing Companion,, Dec. 2013 3 Particle Swarm Optimization PSO Ref: M. Kirschenbaum and D. W. Palmer, “Perceptualization of particle swarm optimization,” in Proceedings of the Swarm/Human Blended Intelligence Workshop, Sep. 2015 1 Grid Search GS Ref: F. Xue, D. Wei, Z. Wang, T. Li, Y. Hu, and H. Huang, “Grid searching method in spherical coordinate for PD location in a substation,” International Conference on Condition Monitoring and Diagnosis, Sep. 2018 5 Sequential Model-based Algorithm Configuration SMAC Ref: M. Zhao and J. Li, “Tuning the hyper-parameters of CMA-ES with tree-structured Parzen estimators,” International Conference on Advanced Computational Intelligence, Mar. 2018 5 8
  • 9. Experimental setup IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Setup A B C Total # of devices 1,200 1,200 1,200 # of models 2 1. MobileNet 2. DenseNet169 3 1. MobileNet 2. DenseNet169 3. ResNet50 4 1. MobileNet 2. DenseNet169 3. ResNet50 4. VGG16 # of devices per model 600 400 300 # of images per model 24,000 16,000 12,000 9
  • 10. Model specification IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 10
  • 11. Datasets IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Name # of images # of output classes CIFAR-10[1] 70,000 10 CIFAR-100[2] 70,000 100 ImageNet[3] 100,000 1,000 R-Cellular[4] 73,000 1,108 References: [1] https://www.cs.toronto.edu/~kriz/cifar.html#CIFAR-10 [2] https://www.cs.toronto.edu/~kriz/cifar.html#CIFAR-100 [3] http://image-net.org/download [4] https://www.kaggle.com/c/recursion-cellular-image-classification 11
  • 12. Optimized weights IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Experimental Setup ➢ Setup C Dataset ➢ CIFAR-10 Optimization ➢ TPE 12
  • 13. Improvement of accuracy IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Experimental Setup A & R-Cellular Dataset 63.19% (before optimizing the weights) 13
  • 14. Accuracy & Runtime IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 Experimental Setup A & R-Cellular Dataset 14
  • 15. Conclusion IEEE International Conference on Machine Learning and Applications 2020, December 14 - 17, 2020 ➢ We proposed a novel method to ensemble neural network models with heterogeneous structures for federated learning ➢ We compared six optimization algorithms to tune the weights for the output classes of each model and found that TPE was able to achieve the highest accuracy We will investigate other parameter optimization methods and federated learning algorithms 15
  • 16. Q&A Thank you for your attention Email: thonglek.kundjanasith.ti7@is.naist.jp