SlideShare a Scribd company logo
FEDBN: FEDERATED LEARNING
ON NON-IID FEATURES VIA LOCAL
BATCH NORMALIZATION
Paper presentation by Anam ur rehman
Contact: anamur.rehman@studenti.polito.it
Published as a conference paper at ICLR 2021
1
Authors
2
FEDBN: Federated learning[1]
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
[1] Jakub et al. Federated optimization: Distributed machine learning for on-device intelligence. 2016
Classical Machine Learning:
• Centralized data storage
• Training process computations at the central server.
What if ?
 Data stays distributed on remote devices
Devices maintain control of their own data
 Training is done locally on remote devices
 One global model is learned via aggregation
3
Autonomous cars on an
average generate around 4 GB
of data per hour of driving.
FEDBN: Federated learning
Applications [1]
• Transportation: self-driving cars
• Healthcare: predictions on patient data
• Cybersecurity: spam filtering
• Smart applications: voice recognition, next word prediction, etc.
[1] Read more: Priyanka et al. Federated Learning: Opportunities and Challenges, 2021
Challenges [1]
• Communication Overheads: presence of stragglers
• Heterogeneity: system, statistical (in contrast to distributed learning)
• Privacy concerns
4
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
FEDBN: Federated learning
Statistical heterogeneity among local datasets:
• Unbalancedness: Clients may have different amount of data
 Example, Spam filter for emails.
• Covariate shift: Statistical distribution of data varies among clients
 Example: NLP digits recognition
• Concept shift: Same features may correspond to different labels for different clients
 Example, in NLP, Sentiment analysis on same text may yield different sentiments for different clients
5
FEDBN: Example of NonIID datasets
MNIST
MNIST-M
USPS SynthDigits
SVHN
Covariate shift among datasets
Digits
dataset
6
FEDBN: Related work
• FedAvg[1]: Federated Average
[1] Brendan McMahan et al. Communication-efficient learning of deep networks from decentralized data. 2017.
At each communication round
1. Server randomly selects a subset of K clients and Send them current global model
2. Selected device k updates this model on local client data via SGD. After training client
sends the new local model back to server
3. Server aggregates local models to form a new global model
- Convergence in not guranteed. In hetergeneous settings it can diverge [1]
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
7
FEDBN: Related work
• FedProx[1]: Federated Optimization in Heterogeneous Networks
[1] Tian Li et al, In Conference on Machine Learning and Systems, 2020a, 2020b.
Slide credit: Tian Li, MLSys presentation.
+ Limits the impact of heterogeneous local updates
+ Safely incorporate partial work of stragglers
+ Generalization of FedAvg; Allows for any local solver
+ Theoretical guarantees for convergence
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
8
FEDBN: Related work
• SiloBN[1]: Siloed Federated Learning for Multi-Centric Histopathology Datasets
[1] Mathieu Andreux et al, Siloed federated learning for multi-centric histopathology datasets, pp. 129–139. Springer, 2020.
Slide credits: [1]
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
9
FEDBN: Batch Normalization
Year
2021
2020
2018
2017
2016
2015
2014
2013
2012
2011
[1] Sergey Ioffe et al. Batch normalization: Accelerating deep network training by reducing internal covariate shift. 2015
γ and β are the only
learnable parameters
of BN layer.
10
Why we use it ?
To reduce internal covariate
shift in neural network [1].
How it works ?
11
2021
FEDBN: Problem with non IID data
12
Consider a simple,
non-convex learning problem:
s.t
ϵ ∼ 𝒩 0, σ2
𝑤2
∗
Two clients train a model
s.t
x1 ∼ 𝒩 μ, σ1
2
.
x2 ∼ 𝒩 μ, σ2
2
.
and
σ1
2
≠ σ2
2
local squared loss before and after local BN
𝑤1
∗
w
𝑓𝑤 𝑥𝑖 = 𝑐𝑜𝑠 𝑤𝑥𝑖
FEDBN: Why not just take the average? (SiloBN)
Client 1
w1
∗
: Optimal weight
γ1
∗
: Optimal BN parameter
Observation 1:
For a fixed optimal weight w1
∗
,
changing γ deteriorates the model
quality.
Observation 2:
For a given optimal BN
parameter γ1
∗
, changing w
deteriorates the quality.
13
FEDBN: How it works?
Local training
Global aggregation
14
FEDBN: Pytorch implementation
15
FEDBN: How it Really Works?
Source: med-air/FedBN (github.com)
16
Global
Aggregation
FEDBN: Results on digit dataset (FedAvg vs FedBN)
• Outperforms FedAvg on SVHN dataset
• Faster convergence
• Smooth and robust convergence
17
FEDBN: Results; what if
Communication is done
at different frequencies?
18
FEDBN: Results; what if
Dataset size varies for
each client?
19
FEDBN: Contributions
Provides convergence guarantees.
Improves the convergence behavior on non-IID datasets.
One step further in privacy of client’s data.
20
FEDBN: Take home message
• Use batch normalization
• Keep it local
• Smooth and fast convergence
21
Useful links
Federated Optimization in Heterogeneous Networks
FedProx presentation by Tian Li:
22
med-air/FedBN (github.com)
Pytorch implementation of FedBN:
Brendan McMahan’s Talk:
Guarding user Privacy with Federated Learning

More Related Content

What's hot

Snmp
SnmpSnmp
Nfs
NfsNfs
Energy consumption of wsn
Energy consumption of wsnEnergy consumption of wsn
Energy consumption of wsn
DeepaDasarathan
 
Physical Layer of ISO-OSI model and Devices
Physical Layer of ISO-OSI model and DevicesPhysical Layer of ISO-OSI model and Devices
Physical Layer of ISO-OSI model and Devices
Shahid Khan
 
Cross layer design and optimization
Cross layer design and optimizationCross layer design and optimization
Cross layer design and optimization
DANISHAMIN950
 
Blake chpater8
Blake chpater8Blake chpater8
Blake chpater8
RenjanSolis
 
Basics of EBG structures
Basics of EBG structuresBasics of EBG structures
Basics of EBG structures
sumanth75
 
Wireless routing protocols
Wireless routing protocolsWireless routing protocols
Wireless routing protocols
barodia_1437
 
Content-Centric Networking (CCN)
Content-Centric Networking (CCN)Content-Centric Networking (CCN)
Content-Centric Networking (CCN)
Dilum Bandara
 
Ieee standards
Ieee standardsIeee standards
Ieee standards
Bisma Sajid
 
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
ArunChokkalingam
 
802.11n Tutorial
802.11n Tutorial802.11n Tutorial
802.11n Tutorial
gopinathkn
 
Unit 3- OPTICAL SOURCES AND DETECTORS
Unit 3- OPTICAL SOURCES AND DETECTORS Unit 3- OPTICAL SOURCES AND DETECTORS
Unit 3- OPTICAL SOURCES AND DETECTORS
tamil arasan
 
EC3401 Networks security PRAVEEN KUMAR K
EC3401 Networks security PRAVEEN KUMAR KEC3401 Networks security PRAVEEN KUMAR K
EC3401 Networks security PRAVEEN KUMAR K
praveenme12
 
6LoWPAN: An open IoT Networking Protocol
6LoWPAN: An open IoT Networking Protocol6LoWPAN: An open IoT Networking Protocol
6LoWPAN: An open IoT Networking Protocol
Samsung Open Source Group
 

What's hot (15)

Snmp
SnmpSnmp
Snmp
 
Nfs
NfsNfs
Nfs
 
Energy consumption of wsn
Energy consumption of wsnEnergy consumption of wsn
Energy consumption of wsn
 
Physical Layer of ISO-OSI model and Devices
Physical Layer of ISO-OSI model and DevicesPhysical Layer of ISO-OSI model and Devices
Physical Layer of ISO-OSI model and Devices
 
Cross layer design and optimization
Cross layer design and optimizationCross layer design and optimization
Cross layer design and optimization
 
Blake chpater8
Blake chpater8Blake chpater8
Blake chpater8
 
Basics of EBG structures
Basics of EBG structuresBasics of EBG structures
Basics of EBG structures
 
Wireless routing protocols
Wireless routing protocolsWireless routing protocols
Wireless routing protocols
 
Content-Centric Networking (CCN)
Content-Centric Networking (CCN)Content-Centric Networking (CCN)
Content-Centric Networking (CCN)
 
Ieee standards
Ieee standardsIeee standards
Ieee standards
 
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
WSN network architecture -Sensor Network Scenarios & Transceiver Design Consi...
 
802.11n Tutorial
802.11n Tutorial802.11n Tutorial
802.11n Tutorial
 
Unit 3- OPTICAL SOURCES AND DETECTORS
Unit 3- OPTICAL SOURCES AND DETECTORS Unit 3- OPTICAL SOURCES AND DETECTORS
Unit 3- OPTICAL SOURCES AND DETECTORS
 
EC3401 Networks security PRAVEEN KUMAR K
EC3401 Networks security PRAVEEN KUMAR KEC3401 Networks security PRAVEEN KUMAR K
EC3401 Networks security PRAVEEN KUMAR K
 
6LoWPAN: An open IoT Networking Protocol
6LoWPAN: An open IoT Networking Protocol6LoWPAN: An open IoT Networking Protocol
6LoWPAN: An open IoT Networking Protocol
 

Similar to FedBN

Knowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical GuideKnowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical Guide
XiachongFeng
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 
TIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdfTIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdf
BoahKim2
 
End-to-end deep auto-encoder for segmenting a moving object with limited tra...
End-to-end deep auto-encoder for segmenting a moving object  with limited tra...End-to-end deep auto-encoder for segmenting a moving object  with limited tra...
End-to-end deep auto-encoder for segmenting a moving object with limited tra...
IJECEIAES
 
Fundamentals of Deep Recommender Systems
 Fundamentals of Deep Recommender Systems Fundamentals of Deep Recommender Systems
Fundamentals of Deep Recommender Systems
WQ Fan
 
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
Universitat Politècnica de Catalunya
 
Large Scale Distributed Deep Networks
Large Scale Distributed Deep NetworksLarge Scale Distributed Deep Networks
Large Scale Distributed Deep Networks
Hiroyuki Vincent Yamazaki
 
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
multimediaeval
 
Presentation_final.pdf
Presentation_final.pdfPresentation_final.pdf
Presentation_final.pdf
ManishKumarMaurya12
 
Mortgage Data for Machine Learning Algorithms
Mortgage Data for Machine Learning AlgorithmsMortgage Data for Machine Learning Algorithms
Mortgage Data for Machine Learning Algorithms
Anne Klieve
 
IRJET- A Review on Object Tracking based on KNN Classifier
IRJET- A Review on Object Tracking based on KNN ClassifierIRJET- A Review on Object Tracking based on KNN Classifier
IRJET- A Review on Object Tracking based on KNN Classifier
IRJET Journal
 
The Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service NetworksThe Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service Networks
Tokyo University of Science
 
Federated learning and its role in the privacy preservation of IoT devices
Federated learning and its role in the privacy preservation of IoT devicesFederated learning and its role in the privacy preservation of IoT devices
Federated learning and its role in the privacy preservation of IoT devices
AlAtfat
 
SEBD2015_PresentationVitali
SEBD2015_PresentationVitaliSEBD2015_PresentationVitali
SEBD2015_PresentationVitali
Monica Vitali
 
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET Journal
 
Grammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world ApplicabilityGrammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world Applicability
Masato Mita
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
Sudeep Das, Ph.D.
 
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWFACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
IRJET Journal
 
Mis 589 Success Begins / snaptutorial.com
Mis 589  Success Begins / snaptutorial.comMis 589  Success Begins / snaptutorial.com
Mis 589 Success Begins / snaptutorial.com
WilliamsTaylor44
 
Mis 589 Massive Success / snaptutorial.com
Mis 589 Massive Success / snaptutorial.comMis 589 Massive Success / snaptutorial.com
Mis 589 Massive Success / snaptutorial.com
Stephenson185
 

Similar to FedBN (20)

Knowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical GuideKnowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical Guide
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
 
TIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdfTIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdf
 
End-to-end deep auto-encoder for segmenting a moving object with limited tra...
End-to-end deep auto-encoder for segmenting a moving object  with limited tra...End-to-end deep auto-encoder for segmenting a moving object  with limited tra...
End-to-end deep auto-encoder for segmenting a moving object with limited tra...
 
Fundamentals of Deep Recommender Systems
 Fundamentals of Deep Recommender Systems Fundamentals of Deep Recommender Systems
Fundamentals of Deep Recommender Systems
 
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
Transfer Learning and Domain Adaptation (DLAI D5L2 2017 UPC Deep Learning for...
 
Large Scale Distributed Deep Networks
Large Scale Distributed Deep NetworksLarge Scale Distributed Deep Networks
Large Scale Distributed Deep Networks
 
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
Efficient Supervision Net: Polyp Segmentation using EfficientNet and Attentio...
 
Presentation_final.pdf
Presentation_final.pdfPresentation_final.pdf
Presentation_final.pdf
 
Mortgage Data for Machine Learning Algorithms
Mortgage Data for Machine Learning AlgorithmsMortgage Data for Machine Learning Algorithms
Mortgage Data for Machine Learning Algorithms
 
IRJET- A Review on Object Tracking based on KNN Classifier
IRJET- A Review on Object Tracking based on KNN ClassifierIRJET- A Review on Object Tracking based on KNN Classifier
IRJET- A Review on Object Tracking based on KNN Classifier
 
The Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service NetworksThe Declarative-Coordinated Model for Self-Optimization of Service Networks
The Declarative-Coordinated Model for Self-Optimization of Service Networks
 
Federated learning and its role in the privacy preservation of IoT devices
Federated learning and its role in the privacy preservation of IoT devicesFederated learning and its role in the privacy preservation of IoT devices
Federated learning and its role in the privacy preservation of IoT devices
 
SEBD2015_PresentationVitali
SEBD2015_PresentationVitaliSEBD2015_PresentationVitali
SEBD2015_PresentationVitali
 
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
 
Grammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world ApplicabilityGrammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world Applicability
 
Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
 
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEWFACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
FACE PHOTO-SKETCH RECOGNITION USING DEEP LEARNING TECHNIQUES - A REVIEW
 
Mis 589 Success Begins / snaptutorial.com
Mis 589  Success Begins / snaptutorial.comMis 589  Success Begins / snaptutorial.com
Mis 589 Success Begins / snaptutorial.com
 
Mis 589 Massive Success / snaptutorial.com
Mis 589 Massive Success / snaptutorial.comMis 589 Massive Success / snaptutorial.com
Mis 589 Massive Success / snaptutorial.com
 

Recently uploaded

Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
TinyAnderson
 
Bob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdfBob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdf
Texas Alliance of Groundwater Districts
 
8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf
by6843629
 
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
hozt8xgk
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
Anagha Prasad
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
Sérgio Sacani
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
HongcNguyn6
 
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
Abdul Wali Khan University Mardan,kP,Pakistan
 
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of ProteinsGBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
Areesha Ahmad
 
Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
International Food Policy Research Institute- South Asia Office
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
Daniel Tubbenhauer
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
Leonel Morgado
 
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptxThe use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
MAGOTI ERNEST
 
Randomised Optimisation Algorithms in DAPHNE
Randomised Optimisation Algorithms in DAPHNERandomised Optimisation Algorithms in DAPHNE
Randomised Optimisation Algorithms in DAPHNE
University of Maribor
 
20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx
Sharon Liu
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
terusbelajar5
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
Advanced-Concepts-Team
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
Gokturk Mehmet Dilci
 
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Leonel Morgado
 

Recently uploaded (20)

Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
 
Bob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdfBob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdf
 
8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf
 
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
 
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
 
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of ProteinsGBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
 
Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
 
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptxThe use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
The use of Nauplii and metanauplii artemia in aquaculture (brine shrimp).pptx
 
Randomised Optimisation Algorithms in DAPHNE
Randomised Optimisation Algorithms in DAPHNERandomised Optimisation Algorithms in DAPHNE
Randomised Optimisation Algorithms in DAPHNE
 
20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
 
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...
 

FedBN

  • 1. FEDBN: FEDERATED LEARNING ON NON-IID FEATURES VIA LOCAL BATCH NORMALIZATION Paper presentation by Anam ur rehman Contact: anamur.rehman@studenti.polito.it Published as a conference paper at ICLR 2021 1
  • 3. FEDBN: Federated learning[1] Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011 [1] Jakub et al. Federated optimization: Distributed machine learning for on-device intelligence. 2016 Classical Machine Learning: • Centralized data storage • Training process computations at the central server. What if ?  Data stays distributed on remote devices Devices maintain control of their own data  Training is done locally on remote devices  One global model is learned via aggregation 3 Autonomous cars on an average generate around 4 GB of data per hour of driving.
  • 4. FEDBN: Federated learning Applications [1] • Transportation: self-driving cars • Healthcare: predictions on patient data • Cybersecurity: spam filtering • Smart applications: voice recognition, next word prediction, etc. [1] Read more: Priyanka et al. Federated Learning: Opportunities and Challenges, 2021 Challenges [1] • Communication Overheads: presence of stragglers • Heterogeneity: system, statistical (in contrast to distributed learning) • Privacy concerns 4 Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011
  • 5. FEDBN: Federated learning Statistical heterogeneity among local datasets: • Unbalancedness: Clients may have different amount of data  Example, Spam filter for emails. • Covariate shift: Statistical distribution of data varies among clients  Example: NLP digits recognition • Concept shift: Same features may correspond to different labels for different clients  Example, in NLP, Sentiment analysis on same text may yield different sentiments for different clients 5
  • 6. FEDBN: Example of NonIID datasets MNIST MNIST-M USPS SynthDigits SVHN Covariate shift among datasets Digits dataset 6
  • 7. FEDBN: Related work • FedAvg[1]: Federated Average [1] Brendan McMahan et al. Communication-efficient learning of deep networks from decentralized data. 2017. At each communication round 1. Server randomly selects a subset of K clients and Send them current global model 2. Selected device k updates this model on local client data via SGD. After training client sends the new local model back to server 3. Server aggregates local models to form a new global model - Convergence in not guranteed. In hetergeneous settings it can diverge [1] Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011 7
  • 8. FEDBN: Related work • FedProx[1]: Federated Optimization in Heterogeneous Networks [1] Tian Li et al, In Conference on Machine Learning and Systems, 2020a, 2020b. Slide credit: Tian Li, MLSys presentation. + Limits the impact of heterogeneous local updates + Safely incorporate partial work of stragglers + Generalization of FedAvg; Allows for any local solver + Theoretical guarantees for convergence Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011 8
  • 9. FEDBN: Related work • SiloBN[1]: Siloed Federated Learning for Multi-Centric Histopathology Datasets [1] Mathieu Andreux et al, Siloed federated learning for multi-centric histopathology datasets, pp. 129–139. Springer, 2020. Slide credits: [1] Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011 9
  • 10. FEDBN: Batch Normalization Year 2021 2020 2018 2017 2016 2015 2014 2013 2012 2011 [1] Sergey Ioffe et al. Batch normalization: Accelerating deep network training by reducing internal covariate shift. 2015 γ and β are the only learnable parameters of BN layer. 10 Why we use it ? To reduce internal covariate shift in neural network [1]. How it works ?
  • 12. FEDBN: Problem with non IID data 12 Consider a simple, non-convex learning problem: s.t ϵ ∼ 𝒩 0, σ2 𝑤2 ∗ Two clients train a model s.t x1 ∼ 𝒩 μ, σ1 2 . x2 ∼ 𝒩 μ, σ2 2 . and σ1 2 ≠ σ2 2 local squared loss before and after local BN 𝑤1 ∗ w 𝑓𝑤 𝑥𝑖 = 𝑐𝑜𝑠 𝑤𝑥𝑖
  • 13. FEDBN: Why not just take the average? (SiloBN) Client 1 w1 ∗ : Optimal weight γ1 ∗ : Optimal BN parameter Observation 1: For a fixed optimal weight w1 ∗ , changing γ deteriorates the model quality. Observation 2: For a given optimal BN parameter γ1 ∗ , changing w deteriorates the quality. 13
  • 14. FEDBN: How it works? Local training Global aggregation 14
  • 16. FEDBN: How it Really Works? Source: med-air/FedBN (github.com) 16 Global Aggregation
  • 17. FEDBN: Results on digit dataset (FedAvg vs FedBN) • Outperforms FedAvg on SVHN dataset • Faster convergence • Smooth and robust convergence 17
  • 18. FEDBN: Results; what if Communication is done at different frequencies? 18
  • 19. FEDBN: Results; what if Dataset size varies for each client? 19
  • 20. FEDBN: Contributions Provides convergence guarantees. Improves the convergence behavior on non-IID datasets. One step further in privacy of client’s data. 20
  • 21. FEDBN: Take home message • Use batch normalization • Keep it local • Smooth and fast convergence 21
  • 22. Useful links Federated Optimization in Heterogeneous Networks FedProx presentation by Tian Li: 22 med-air/FedBN (github.com) Pytorch implementation of FedBN: Brendan McMahan’s Talk: Guarding user Privacy with Federated Learning