SlideShare a Scribd company logo
1 of 13
Masayuki Tanaka
Breaking Inter-Layer Co-Adaptation
by Classifier Anonymization
Ikuro Sato†, Kohta Ishikawa†, Guoqing Liu†, Masayuki Tanaka‡
(ICML2019)
† ‡
Meta reviewer’s comment
…This paper seems to me like a perfect example of a
“High Risk High Reward” paper, …
Acceptance ratio of ICML2019: 773/3424 = 22.6%
We have taken that as a compliment. It is a research!
1
What I’m going to talk
𝑥𝑥
Input
𝐹𝐹𝜙𝜙(𝑥𝑥) 𝐶𝐶𝜃𝜃(𝜉𝜉)
𝜂𝜂
Output
𝜉𝜉
Feature
Let’s consider a classification task.
Feature extractor Classifier
+
-
Feature space 𝜉𝜉
+
+
+ +
+
+ +
--
-
-
-- -
-
Feature space 𝜉𝜉
+
++
+
+
+
+-- --
--
-
End-to-end DNN
<<
Which is better? Why? How can we obtain good features?2
Summary
About what?
How?
Theory?
In reality?
Breaking co-adaptation between
feature extractor and classifier.
By classifier anonymization technique.
Proved: Features form simple
point-like distribution.
Point-like property largely confirmed
on real datasets.
3
What is a co-adaptation?
𝑥𝑥
Input
𝐹𝐹𝜙𝜙(𝑥𝑥) 𝐶𝐶𝜃𝜃(𝜉𝜉)
𝜂𝜂
Output
𝜉𝜉
Feature
Let’s consider a classification task.
Feature extractor Classifier
+
-
Feature space 𝜉𝜉
Decision
boundary
+
+
+ +
+
+ +
--
-
-
-- -
Co-adaptation:
Feature extractor adapts a particular classifier.
Classifier adapts a particular feature extractor.
Break
co-adaptation
-
Feature space 𝜉𝜉
+
++
+
+
+
+-- --
--
-
Classifiers
Feature extractor should be
trained for many classifiers.
End-to-end DNN
4
Proposed algorithm: FOCA
-
Feature space 𝜉𝜉
+++
+
+ ++
--
-----
(Under several conditions,)
we theoretically proved the FOCA
can train the feature extractor
which projects single point.
for given feature extractor
FOCA can train feature extractor to make any weak classifier strong.
FOCA:
Feature-extractor Optimization through Classifier Anonymization
5
Message of FOCA
Traditional training FOCA training
Feature extractor
(Junior researcher)
Feature extractor
(Junior researcher)
Weak classifiers
(Boss variety???)
Strong classifier
(Smart boss)
Transfer learning
(New boss, new domain)
FOCA can train
feature extractor strong.
6
Weak classifier assumption
Definition:
Weak classifier is slightly better than random guess.
𝜃𝜃𝜙𝜙
∗
= arg min
𝜃𝜃
E
(𝑥𝑥,𝑡𝑡)~𝑝𝑝(𝑥𝑥,𝑡𝑡)
𝐿𝐿 𝐶𝐶𝜃𝜃 𝐹𝐹𝜙𝜙(𝑥𝑥) , 𝑡𝑡
𝜃𝜃𝜙𝜙
𝐵𝐵
= arg min
𝜃𝜃
�
𝑥𝑥,𝑡𝑡 ∈𝐵𝐵
𝐿𝐿 𝐶𝐶𝜃𝜃 𝐹𝐹𝜙𝜙(𝑥𝑥) , 𝑡𝑡
Strong classifier
Strong classifier is strong for entire data.
Weak classifier assumption
We assume that strong classifier for small samples is
weak classifier for entire data.
B is small samples of entire data.
7
Practical FOCA algorithm
𝐹𝐹𝜙𝜙(𝑥𝑥)
𝐶𝐶𝜃𝜃(𝜉𝜉)
Weak classifier
generatorFeature
extractor
Classifier model
𝐹𝐹𝐹𝜙𝜙(𝑥𝑥)
Previous
feature extractor
Training data
Optimize the classifier
for given small samples
with previous feature extractor.
Update feature extractor
for given mini-batch
with weak classifier.
Sampling
𝐶𝐶𝜃𝜃(𝜉𝜉)
Weak classifier
Update
Mini-batch
8
Experimental validation
Two-step training:
Train the feature extractor. Then, train the classifier with the fixed
given feature extractor.
-
Feature space 𝜉𝜉
+
+
+ +
+
+ +
--
-
-
-- -
Co-adaptation Point-like
-
Feature space 𝜉𝜉
+++
+
+ ++
--
-----
Many samples are required to train
the classifier.
A few samples are good enough to
train the classifier.
9
Results
10
Poster as a summary
11
Links
Official proceedings of ICML2019
http://proceedings.mlr.press/v97/
arxiv: Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
https://arxiv.org/abs/1906.01150
Twitter: Masayuki Tanaka
https://twitter.com/likesilkto
Twitter: Ikuro Sato
https://twitter.com/ikuro_s
12

More Related Content

What's hot

Optimal feature selection from v mware esxi 5.1 feature set
Optimal feature selection from v mware esxi 5.1 feature setOptimal feature selection from v mware esxi 5.1 feature set
Optimal feature selection from v mware esxi 5.1 feature setijccmsjournal
 
Best practices in Java
Best practices in JavaBest practices in Java
Best practices in JavaMudit Gupta
 
DotNet programming & Practices
DotNet programming & PracticesDotNet programming & Practices
DotNet programming & PracticesDev Raj Gautam
 
(Recursion)ads
(Recursion)ads(Recursion)ads
(Recursion)adsRavi Rao
 
Pattern Matching - at a glance
Pattern Matching - at a glancePattern Matching - at a glance
Pattern Matching - at a glanceKnoldus Inc.
 
Feature selection
Feature selectionFeature selection
Feature selectionDong Guo
 
Feature recognition and classification
Feature recognition and classificationFeature recognition and classification
Feature recognition and classificationSooraz Sresta
 
Data Handling and Function
Data Handling and FunctionData Handling and Function
Data Handling and FunctionRatnaJava
 

What's hot (16)

Fuzzy logic member functions
Fuzzy logic member functionsFuzzy logic member functions
Fuzzy logic member functions
 
Generics
GenericsGenerics
Generics
 
Optimal feature selection from v mware esxi 5.1 feature set
Optimal feature selection from v mware esxi 5.1 feature setOptimal feature selection from v mware esxi 5.1 feature set
Optimal feature selection from v mware esxi 5.1 feature set
 
Best practices in Java
Best practices in JavaBest practices in Java
Best practices in Java
 
Wrapper classes
Wrapper classesWrapper classes
Wrapper classes
 
DotNet programming & Practices
DotNet programming & PracticesDotNet programming & Practices
DotNet programming & Practices
 
(Recursion)ads
(Recursion)ads(Recursion)ads
(Recursion)ads
 
Recursion Pattern Analysis and Feedback
Recursion Pattern Analysis and FeedbackRecursion Pattern Analysis and Feedback
Recursion Pattern Analysis and Feedback
 
Pattern Matching - at a glance
Pattern Matching - at a glancePattern Matching - at a glance
Pattern Matching - at a glance
 
Chapter 11 ds
Chapter 11 dsChapter 11 ds
Chapter 11 ds
 
Java Generics
Java GenericsJava Generics
Java Generics
 
wrapper classes
wrapper classeswrapper classes
wrapper classes
 
Feature selection
Feature selectionFeature selection
Feature selection
 
Generics in java
Generics in javaGenerics in java
Generics in java
 
Feature recognition and classification
Feature recognition and classificationFeature recognition and classification
Feature recognition and classification
 
Data Handling and Function
Data Handling and FunctionData Handling and Function
Data Handling and Function
 

Similar to Slideshare breaking inter layer co-adaptation

Machine learning for document analysis and understanding
Machine learning for document analysis and understandingMachine learning for document analysis and understanding
Machine learning for document analysis and understandingSeiichi Uchida
 
Machine Learning Lecture 3 Decision Trees
Machine Learning Lecture 3 Decision TreesMachine Learning Lecture 3 Decision Trees
Machine Learning Lecture 3 Decision Treesananth
 
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...Waqas Tariq
 
Using CNTK's Python Interface for Deep LearningDave DeBarr -
Using CNTK's Python Interface for Deep LearningDave DeBarr - Using CNTK's Python Interface for Deep LearningDave DeBarr -
Using CNTK's Python Interface for Deep LearningDave DeBarr - PyData
 
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...Annibale Panichella
 
Branch And Bound and Beam Search Feature Selection Algorithms
Branch And Bound and Beam Search Feature Selection AlgorithmsBranch And Bound and Beam Search Feature Selection Algorithms
Branch And Bound and Beam Search Feature Selection AlgorithmsChamin Nalinda Loku Gam Hewage
 
Efficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesEfficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesRui Vieira
 
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learnt
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learntKaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learnt
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learntEugene Yan Ziyou
 
Booting into functional programming
Booting into functional programmingBooting into functional programming
Booting into functional programmingDhaval Dalal
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...MLAI2
 
Foundations: Artificial Neural Networks
Foundations: Artificial Neural NetworksFoundations: Artificial Neural Networks
Foundations: Artificial Neural Networksananth
 
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...Jimmy Lai
 
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017StampedeCon
 

Similar to Slideshare breaking inter layer co-adaptation (20)

Machine learning for document analysis and understanding
Machine learning for document analysis and understandingMachine learning for document analysis and understanding
Machine learning for document analysis and understanding
 
Machine Learning Lecture 3 Decision Trees
Machine Learning Lecture 3 Decision TreesMachine Learning Lecture 3 Decision Trees
Machine Learning Lecture 3 Decision Trees
 
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...
Reconstruction of a Complete Dataset from an Incomplete Dataset by ARA (Attri...
 
Using CNTK's Python Interface for Deep LearningDave DeBarr -
Using CNTK's Python Interface for Deep LearningDave DeBarr - Using CNTK's Python Interface for Deep LearningDave DeBarr -
Using CNTK's Python Interface for Deep LearningDave DeBarr -
 
Spark Meetup
Spark MeetupSpark Meetup
Spark Meetup
 
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...
Parameterizing and Assembling IR-based Solutions for SE Tasks using Genetic A...
 
Text analysis using python
Text analysis using pythonText analysis using python
Text analysis using python
 
Branch And Bound and Beam Search Feature Selection Algorithms
Branch And Bound and Beam Search Feature Selection AlgorithmsBranch And Bound and Beam Search Feature Selection Algorithms
Branch And Bound and Beam Search Feature Selection Algorithms
 
supervised.pptx
supervised.pptxsupervised.pptx
supervised.pptx
 
Efficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesEfficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databases
 
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learnt
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learntKaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learnt
Kaggle Otto Challenge: How we achieved 85th out of 3,514 and what we learnt
 
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
 
Booting into functional programming
Booting into functional programmingBooting into functional programming
Booting into functional programming
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
Python master class 2
Python master class 2Python master class 2
Python master class 2
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
 
Foundations: Artificial Neural Networks
Foundations: Artificial Neural NetworksFoundations: Artificial Neural Networks
Foundations: Artificial Neural Networks
 
2017 nov reflow sbtb
2017 nov reflow sbtb2017 nov reflow sbtb
2017 nov reflow sbtb
 
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...
Text Classification in Python – using Pandas, scikit-learn, IPython Notebook ...
 
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
Getting Started with Keras and TensorFlow - StampedeCon AI Summit 2017
 

More from Masayuki Tanaka

PRMU201902 Presentation document
PRMU201902 Presentation documentPRMU201902 Presentation document
PRMU201902 Presentation documentMasayuki Tanaka
 
Gradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementGradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementMasayuki Tanaka
 
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得Masayuki Tanaka
 
Learnable Image Encryption
Learnable Image EncryptionLearnable Image Encryption
Learnable Image EncryptionMasayuki Tanaka
 
クリエイティブ・コモンズ
クリエイティブ・コモンズクリエイティブ・コモンズ
クリエイティブ・コモンズMasayuki Tanaka
 
メラビアンの法則
メラビアンの法則メラビアンの法則
メラビアンの法則Masayuki Tanaka
 
権威に訴える論証
権威に訴える論証権威に訴える論証
権威に訴える論証Masayuki Tanaka
 
Chain rule of deep neural network layer for back propagation
Chain rule of deep neural network layer for back propagationChain rule of deep neural network layer for back propagation
Chain rule of deep neural network layer for back propagationMasayuki Tanaka
 
One-point for presentation
One-point for presentationOne-point for presentation
One-point for presentationMasayuki Tanaka
 
ADMM algorithm in ProxImaL
ADMM algorithm in ProxImaL ADMM algorithm in ProxImaL
ADMM algorithm in ProxImaL Masayuki Tanaka
 
Intensity Constraint Gradient-Based Image Reconstruction
Intensity Constraint Gradient-Based Image ReconstructionIntensity Constraint Gradient-Based Image Reconstruction
Intensity Constraint Gradient-Based Image ReconstructionMasayuki Tanaka
 
Least Square with L0, L1, and L2 Constraint
Least Square with L0, L1, and L2 ConstraintLeast Square with L0, L1, and L2 Constraint
Least Square with L0, L1, and L2 ConstraintMasayuki Tanaka
 

More from Masayuki Tanaka (20)

PRMU201902 Presentation document
PRMU201902 Presentation documentPRMU201902 Presentation document
PRMU201902 Presentation document
 
Gradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image EnhancementGradient-Based Low-Light Image Enhancement
Gradient-Based Low-Light Image Enhancement
 
Year-End Seminar 2018
Year-End Seminar 2018Year-End Seminar 2018
Year-End Seminar 2018
 
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
 
Learnable Image Encryption
Learnable Image EncryptionLearnable Image Encryption
Learnable Image Encryption
 
クリエイティブ・コモンズ
クリエイティブ・コモンズクリエイティブ・コモンズ
クリエイティブ・コモンズ
 
デザイン4原則
デザイン4原則デザイン4原則
デザイン4原則
 
メラビアンの法則
メラビアンの法則メラビアンの法則
メラビアンの法則
 
類似性の法則
類似性の法則類似性の法則
類似性の法則
 
権威に訴える論証
権威に訴える論証権威に訴える論証
権威に訴える論証
 
Chain rule of deep neural network layer for back propagation
Chain rule of deep neural network layer for back propagationChain rule of deep neural network layer for back propagation
Chain rule of deep neural network layer for back propagation
 
Give Me Four
Give Me FourGive Me Four
Give Me Four
 
Tech art 20170315
Tech art 20170315Tech art 20170315
Tech art 20170315
 
My Slide Theme
My Slide ThemeMy Slide Theme
My Slide Theme
 
Font Memo
Font MemoFont Memo
Font Memo
 
One-point for presentation
One-point for presentationOne-point for presentation
One-point for presentation
 
ADMM algorithm in ProxImaL
ADMM algorithm in ProxImaL ADMM algorithm in ProxImaL
ADMM algorithm in ProxImaL
 
Intensity Constraint Gradient-Based Image Reconstruction
Intensity Constraint Gradient-Based Image ReconstructionIntensity Constraint Gradient-Based Image Reconstruction
Intensity Constraint Gradient-Based Image Reconstruction
 
Least Square with L0, L1, and L2 Constraint
Least Square with L0, L1, and L2 ConstraintLeast Square with L0, L1, and L2 Constraint
Least Square with L0, L1, and L2 Constraint
 
Lasso regression
Lasso regressionLasso regression
Lasso regression
 

Recently uploaded

Harmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms PresentationHarmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms Presentationtahreemzahra82
 
Servosystem Theory / Cybernetic Theory by Petrovic
Servosystem Theory / Cybernetic Theory by PetrovicServosystem Theory / Cybernetic Theory by Petrovic
Servosystem Theory / Cybernetic Theory by PetrovicAditi Jain
 
User Guide: Orion™ Weather Station (Columbia Weather Systems)
User Guide: Orion™ Weather Station (Columbia Weather Systems)User Guide: Orion™ Weather Station (Columbia Weather Systems)
User Guide: Orion™ Weather Station (Columbia Weather Systems)Columbia Weather Systems
 
CHROMATOGRAPHY PALLAVI RAWAT.pptx
CHROMATOGRAPHY  PALLAVI RAWAT.pptxCHROMATOGRAPHY  PALLAVI RAWAT.pptx
CHROMATOGRAPHY PALLAVI RAWAT.pptxpallavirawat456
 
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)Columbia Weather Systems
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...Universidade Federal de Sergipe - UFS
 
GLYCOSIDES Classification Of GLYCOSIDES Chemical Tests Glycosides
GLYCOSIDES Classification Of GLYCOSIDES  Chemical Tests GlycosidesGLYCOSIDES Classification Of GLYCOSIDES  Chemical Tests Glycosides
GLYCOSIDES Classification Of GLYCOSIDES Chemical Tests GlycosidesNandakishor Bhaurao Deshmukh
 
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...D. B. S. College Kanpur
 
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationUser Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationColumbia Weather Systems
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxJorenAcuavera1
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPirithiRaju
 
trihybrid cross , test cross chi squares
trihybrid cross , test cross chi squarestrihybrid cross , test cross chi squares
trihybrid cross , test cross chi squaresusmanzain586
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPirithiRaju
 
Organic farming with special reference to vermiculture
Organic farming with special reference to vermicultureOrganic farming with special reference to vermiculture
Organic farming with special reference to vermicultureTakeleZike1
 
well logging & petrophysical analysis.pptx
well logging & petrophysical analysis.pptxwell logging & petrophysical analysis.pptx
well logging & petrophysical analysis.pptxzaydmeerab121
 
Biological classification of plants with detail
Biological classification of plants with detailBiological classification of plants with detail
Biological classification of plants with detailhaiderbaloch3
 
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptx
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptxSTOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptx
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptxMurugaveni B
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPirithiRaju
 
Ai in communication electronicss[1].pptx
Ai in communication electronicss[1].pptxAi in communication electronicss[1].pptx
Ai in communication electronicss[1].pptxsubscribeus100
 

Recently uploaded (20)

Harmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms PresentationHarmful and Useful Microorganisms Presentation
Harmful and Useful Microorganisms Presentation
 
Servosystem Theory / Cybernetic Theory by Petrovic
Servosystem Theory / Cybernetic Theory by PetrovicServosystem Theory / Cybernetic Theory by Petrovic
Servosystem Theory / Cybernetic Theory by Petrovic
 
User Guide: Orion™ Weather Station (Columbia Weather Systems)
User Guide: Orion™ Weather Station (Columbia Weather Systems)User Guide: Orion™ Weather Station (Columbia Weather Systems)
User Guide: Orion™ Weather Station (Columbia Weather Systems)
 
CHROMATOGRAPHY PALLAVI RAWAT.pptx
CHROMATOGRAPHY  PALLAVI RAWAT.pptxCHROMATOGRAPHY  PALLAVI RAWAT.pptx
CHROMATOGRAPHY PALLAVI RAWAT.pptx
 
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
 
GLYCOSIDES Classification Of GLYCOSIDES Chemical Tests Glycosides
GLYCOSIDES Classification Of GLYCOSIDES  Chemical Tests GlycosidesGLYCOSIDES Classification Of GLYCOSIDES  Chemical Tests Glycosides
GLYCOSIDES Classification Of GLYCOSIDES Chemical Tests Glycosides
 
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
 
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather StationUser Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather Station
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptx
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
 
trihybrid cross , test cross chi squares
trihybrid cross , test cross chi squarestrihybrid cross , test cross chi squares
trihybrid cross , test cross chi squares
 
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdfPests of jatropha_Bionomics_identification_Dr.UPR.pdf
Pests of jatropha_Bionomics_identification_Dr.UPR.pdf
 
Organic farming with special reference to vermiculture
Organic farming with special reference to vermicultureOrganic farming with special reference to vermiculture
Organic farming with special reference to vermiculture
 
well logging & petrophysical analysis.pptx
well logging & petrophysical analysis.pptxwell logging & petrophysical analysis.pptx
well logging & petrophysical analysis.pptx
 
Biological classification of plants with detail
Biological classification of plants with detailBiological classification of plants with detail
Biological classification of plants with detail
 
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptx
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptxSTOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptx
STOPPED FLOW METHOD & APPLICATION MURUGAVENI B.pptx
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
 
AZOTOBACTER AS BIOFERILIZER.PPTX
AZOTOBACTER AS BIOFERILIZER.PPTXAZOTOBACTER AS BIOFERILIZER.PPTX
AZOTOBACTER AS BIOFERILIZER.PPTX
 
Ai in communication electronicss[1].pptx
Ai in communication electronicss[1].pptxAi in communication electronicss[1].pptx
Ai in communication electronicss[1].pptx
 

Slideshare breaking inter layer co-adaptation

  • 1. Masayuki Tanaka Breaking Inter-Layer Co-Adaptation by Classifier Anonymization Ikuro Sato†, Kohta Ishikawa†, Guoqing Liu†, Masayuki Tanaka‡ (ICML2019) † ‡
  • 2. Meta reviewer’s comment …This paper seems to me like a perfect example of a “High Risk High Reward” paper, … Acceptance ratio of ICML2019: 773/3424 = 22.6% We have taken that as a compliment. It is a research! 1
  • 3. What I’m going to talk 𝑥𝑥 Input 𝐹𝐹𝜙𝜙(𝑥𝑥) 𝐶𝐶𝜃𝜃(𝜉𝜉) 𝜂𝜂 Output 𝜉𝜉 Feature Let’s consider a classification task. Feature extractor Classifier + - Feature space 𝜉𝜉 + + + + + + + -- - - -- - - Feature space 𝜉𝜉 + ++ + + + +-- -- -- - End-to-end DNN << Which is better? Why? How can we obtain good features?2
  • 4. Summary About what? How? Theory? In reality? Breaking co-adaptation between feature extractor and classifier. By classifier anonymization technique. Proved: Features form simple point-like distribution. Point-like property largely confirmed on real datasets. 3
  • 5. What is a co-adaptation? 𝑥𝑥 Input 𝐹𝐹𝜙𝜙(𝑥𝑥) 𝐶𝐶𝜃𝜃(𝜉𝜉) 𝜂𝜂 Output 𝜉𝜉 Feature Let’s consider a classification task. Feature extractor Classifier + - Feature space 𝜉𝜉 Decision boundary + + + + + + + -- - - -- - Co-adaptation: Feature extractor adapts a particular classifier. Classifier adapts a particular feature extractor. Break co-adaptation - Feature space 𝜉𝜉 + ++ + + + +-- -- -- - Classifiers Feature extractor should be trained for many classifiers. End-to-end DNN 4
  • 6. Proposed algorithm: FOCA - Feature space 𝜉𝜉 +++ + + ++ -- ----- (Under several conditions,) we theoretically proved the FOCA can train the feature extractor which projects single point. for given feature extractor FOCA can train feature extractor to make any weak classifier strong. FOCA: Feature-extractor Optimization through Classifier Anonymization 5
  • 7. Message of FOCA Traditional training FOCA training Feature extractor (Junior researcher) Feature extractor (Junior researcher) Weak classifiers (Boss variety???) Strong classifier (Smart boss) Transfer learning (New boss, new domain) FOCA can train feature extractor strong. 6
  • 8. Weak classifier assumption Definition: Weak classifier is slightly better than random guess. 𝜃𝜃𝜙𝜙 ∗ = arg min 𝜃𝜃 E (𝑥𝑥,𝑡𝑡)~𝑝𝑝(𝑥𝑥,𝑡𝑡) 𝐿𝐿 𝐶𝐶𝜃𝜃 𝐹𝐹𝜙𝜙(𝑥𝑥) , 𝑡𝑡 𝜃𝜃𝜙𝜙 𝐵𝐵 = arg min 𝜃𝜃 � 𝑥𝑥,𝑡𝑡 ∈𝐵𝐵 𝐿𝐿 𝐶𝐶𝜃𝜃 𝐹𝐹𝜙𝜙(𝑥𝑥) , 𝑡𝑡 Strong classifier Strong classifier is strong for entire data. Weak classifier assumption We assume that strong classifier for small samples is weak classifier for entire data. B is small samples of entire data. 7
  • 9. Practical FOCA algorithm 𝐹𝐹𝜙𝜙(𝑥𝑥) 𝐶𝐶𝜃𝜃(𝜉𝜉) Weak classifier generatorFeature extractor Classifier model 𝐹𝐹𝐹𝜙𝜙(𝑥𝑥) Previous feature extractor Training data Optimize the classifier for given small samples with previous feature extractor. Update feature extractor for given mini-batch with weak classifier. Sampling 𝐶𝐶𝜃𝜃(𝜉𝜉) Weak classifier Update Mini-batch 8
  • 10. Experimental validation Two-step training: Train the feature extractor. Then, train the classifier with the fixed given feature extractor. - Feature space 𝜉𝜉 + + + + + + + -- - - -- - Co-adaptation Point-like - Feature space 𝜉𝜉 +++ + + ++ -- ----- Many samples are required to train the classifier. A few samples are good enough to train the classifier. 9
  • 12. Poster as a summary 11
  • 13. Links Official proceedings of ICML2019 http://proceedings.mlr.press/v97/ arxiv: Breaking Inter-Layer Co-Adaptation by Classifier Anonymization https://arxiv.org/abs/1906.01150 Twitter: Masayuki Tanaka https://twitter.com/likesilkto Twitter: Ikuro Sato https://twitter.com/ikuro_s 12