SlideShare ist ein Scribd-Unternehmen logo
1 von 57
Downloaden Sie, um offline zu lesen
Qu Speaker Series
Explainable AI Workshop
Explaining by Removing: A Unified Framework for Model Explanation
Ian Covert
University of Washington
2020 Copyright QuantUniversity LLC.
Hosted By:
Sri Krishnamurthy, CFA, CAP
sri@quantuniversity.com
www.qu.academy
12/16/2020
Qu.Academy
https://quspeakerseries18.splashthat.com/
2
QuantUniversity
• Boston-based Data Science, Quant
Finance and Machine Learning
training and consulting advisory
• Trained more than 1000 students in
Quantitative methods, Data Science
and Big Data Technologies using
MATLAB, Python and R
• Building a platform for AI
and Machine Learning Exploration
and Experimentation
3
For registration information, go to
https://QuFallSchool.splashthat.com
4
https://Quwinterschool.splashthat.com
5
Next Week
6
7
Demos, slides and video available on QuAcademy
Go to www.qu.academy
7
Explaining by Removing: A Unified
Framework for Model Explanation
Ian Covert
Ian Covert, Scott Lundberg, Su-In Lee. “Explaining by Removing: A Unified
Framework for Model Explanation.” arXiv preprint:2011.14878
Our paper
1. Motivation
2. A unified framework
3. Demonstration
4. Why feature removal?
5. Are there “right” choices?
Contents
> Black-box models increasingly popular
> Explainable AI increasingly important
> Which methods should we rely on?
Motivation
𝑓
> SHAP, LIME, SAGE, Occlusion, DeepLift, SmoothGrad, Integrated
Gradients, GradCAM, CXPlain, L2X, INVASE, Meaningful
Perturbations, Extremal Perturbations, RISE, TCAV, Guided Backprop,
Excitation Backprop, IME, QII, PredDiff, MIR, Permutation Tests, LRP,
FIDO-CA, Masking Model, Expected Gradients, LossSHAP, Shapley
Effects, MP2-G, Saliency Maps, PDPs, ICEs, TreeSHAP, …
Example methods
> Researchers have made significant progress
> The field is fragmented
> Growing very fast
> Lacking discussion of underlying principles
Is the field in a good place?
Monolithic algorithms
à interchangeable
choices
Goals of this talk
A unifying theory
that describes 20+
methods
One key idea about
how to explain ML
models
1. Motivation
2. A unified framework
3. Demonstration
4. Why feature removal?
5. Are there “right” choices?
Contents
> Many methods implicitly simulate feature removal
> Non-trivial operation, different approaches
> Further differences in generating final “explanation”
Explaining by removing
A simple framework
A simple framework
A simple framework
A simple framework
> The model 𝒇 requires a specific set of features
𝒇(𝒙) for 𝒙 ∈ 𝓧
> Require a subset function 𝑭 that accepts a feature subset
𝑭(𝒙 𝑺) for 𝒙 ∈ 𝒳 and 𝑺 ⊆ 𝟏, 𝟐, … , 𝒅
1. Feature removal
> Select a target quantity to explain
§ Individual prediction: 𝒗 𝒙 𝑺 = 𝑭 𝒙 𝑺
§ Prediction loss: 𝒗 𝒙𝒚 𝑺 = − ℓ 𝑭 𝒙 𝑺 , 𝒚
§ Dataset loss: 𝒗 𝑺 = − 𝔼 ℓ 𝑭 𝑿 𝑺 , 𝒀
2. Model behavior
𝑓
> Every method has an underlying set function 𝒗 𝑺
3. Summary technique
> Every method has an underlying set function 𝒗 𝑺
3. Summary technique
> Every method has an underlying set function 𝒗 𝑺
3. Summary technique
> Every method has an underlying set function 𝒗 𝑺
> Explanations provide a concise summary
3. Summary technique
> Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅
Summary types
> Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅
> E.g., remove individual
Summary types
−
> Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅
> E.g., remove individual, include individual
Summary types
−
> Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅
> E.g., remove individual, include individual
> Feature selection: output influential set 𝑺∗ ⊆ 𝟏, 𝟐, … , 𝒅
Summary types
Example methods
> Removal: default values
> Behavior: individual prediction
> Summary: fit linear model
Example: LIME (2016)
> Removal: marginalize out
> Behavior: individual prediction (same as LIME)
> Summary: Shapley value
Example: SHAP (2017)
> Removal: marginalize out (same as SHAP)
> Behavior: dataset loss
> Summary: Shapley value (same as SHAP)
Example: SAGE (2020)
> Removal: marginalize out (same as SAGE)
> Behavior: dataset loss (same as SAGE)
> Summary: remove individual
Example: permutation test (2001)
−
> 20+ existing methods
> Local and global
> Feature attribution and
feature selection
A unifying framework
A unifying framework
Remove
individual
Include
individual
Mean when
included
Shapley value
Linear
model
High value
subset
Low value
subset
Partitioned
subsets
Zeros
Occlusion
CXPlain
RISE MM
Default values
LIME
(images)
Extend pixels MIR
Blurring EP MP
Generative
model
FIDO-CA
Marginalize
(replacement
distribution)
LIME
(tabular)
Marginalize
(uniform)
IME (2010)
Marginalize
(marginals
product)
QII
Marginalize
(marginal)
Permutation
test
SHAP
KernelSHAP
Marginalize
(conditional)
PredDiff
Conditional
perm. test
SHAP SAGE
LossSHAP
Shapley Effects
Tree
distribution
TreeSHAP
Missingness
during training
L2X
INVASE
Separate
models
Feature
ablation
Univariate
predictors
IME (2009)
Shapley Net
Effects
Summary technique
Featureremoval
∎ Prediction ∎ Prediction loss ∎ Mean prediction loss ∎ Dataset loss ∎ Dataset loss (output)Model behavior
Feature attribution Feature selection
> Method “space”
> Neighboring methods
> Unique methods, new
methods
1. Motivation
2. A unified framework
3. Demonstration
4. Why feature removal?
5. Are there “right” choices?
Contents
> GitHub: https://github.com/iancovert/removal-explanations
> Simple implementation of many methods
> Focus on interchangeable choices
Demonstration
Summary
> A new class of methods based on feature removal
> Each method is specified by three choices
> Framework offers a great degree of flexibility
Removal-based explanations
1. Is feature removal a smart approach to model explanation?
2. Are there “right” choices for each dimension?
Key questions
1. Motivation
2. A unified framework
3. Demonstration
4. Why feature removal?
5. Are there “right” choices?
Contents
> Intuitive to many research groups
> Feature removal is a form of counterfactual reasoning
> Undo act of observing information (rather than changing what was
observed)
> Removal is anchored in psychology (subtractive counterfactual) and
philosophy (method of difference)
Why feature removal?
> Counterfactuals change aspects of a situation
(observation of feature values)
> Can understand models by changing inputs
> Often complicated to explore
> Feature removal gives a more practical way to
explore and summarize functions
Counterfactual reasoning
1. Motivation
2. A unified framework
3. Demonstration
4. Why feature removal?
5. Are there “right” choices?
Contents
“Right” choices?
> Methods determined by three choices
> Every method has something to offer
> Conceptual and computational trade-offs
> Marginalizing out features with their conditional
distribution
> Difficult to implement, but many approximations
> Yields information-theoretic explanations
Feature removal strategy
> Intuitively (Chest X-Ray)
> How should a doctor interpret this?
> Mathematically:
𝑭 𝒙 𝑺 = 𝔼 𝒇 𝑿 𝑿 𝑺 = 𝒙 𝑺
= ∫ 𝒑 𝒙(𝑺 𝒙 𝑺 𝒇(𝒙 𝑺, 𝒙(𝑺)
Conditional distribution removal
Information-theoretic explanations
> Any choice provides valuable information
> Range of perspectives
> Depends on use-case
Model behavior
> Precedent in cooperative game theory
> Many potential desirable properties
> Shapley value satisfies most
𝝓𝒊 𝒗 =
𝟏
𝒅
<
𝑺⊆𝑫-
𝒅 − 𝟏
𝑺
.𝟏
𝒗 𝑺 ∪ 𝒊 − 𝒗 𝑺
Summary technique
Game-theoretic explanations
1. Motivation
2. A unified framework
3. Why feature removal?
4. Demonstration
5. Are there “right” choices?
6. Conclusion + questions
Contents
> Presented a new perspective for understanding explainability tools
> Developed rigorous foundations
> Aim to inform practitioners, guide researchers
Concluding thoughts
Questions
56
Instructions for the Lab:
1. Go to https://academy.qusandbox.com/#/register and register using the code:
"QUFALLSCHOOL"
Thank you!
Sri Krishnamurthy, CFA, CAP
Founder and CEO
QuantUniversity LLC.
srikrishnamurthy
www.QuantUniversity.com
Contact
Information, data and drawings embodied in this presentation are strictly a property of QuantUniversity LLC. and shall not be
distributed or used in any other publication without the prior written consent of QuantUniversity LLC.
57

Weitere ähnliche Inhalte

Was ist angesagt?

LearningKit.ppt
LearningKit.pptLearningKit.ppt
LearningKit.ppt
butest
 

Was ist angesagt? (19)

Time series analysis : Refresher and Innovations
Time series analysis : Refresher and InnovationsTime series analysis : Refresher and Innovations
Time series analysis : Refresher and Innovations
 
Andrea Dal Pozzolo's CV
Andrea Dal Pozzolo's CVAndrea Dal Pozzolo's CV
Andrea Dal Pozzolo's CV
 
Human in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIHuman in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AI
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learning
 
Interpretable machine learning
Interpretable machine learningInterpretable machine learning
Interpretable machine learning
 
Applied Artificial Intelligence Unit 4 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 4 Semester 3 MSc IT Part 2 Mumbai Univer...Applied Artificial Intelligence Unit 4 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 4 Semester 3 MSc IT Part 2 Mumbai Univer...
 
Machine Learning Interpretability
Machine Learning InterpretabilityMachine Learning Interpretability
Machine Learning Interpretability
 
The lottery ticket_hypothesis__finding_sparse__trainable_neural_networks
The lottery ticket_hypothesis__finding_sparse__trainable_neural_networksThe lottery ticket_hypothesis__finding_sparse__trainable_neural_networks
The lottery ticket_hypothesis__finding_sparse__trainable_neural_networks
 
Applied Artificial Intelligence Unit 3 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 3 Semester 3 MSc IT Part 2 Mumbai Univer...Applied Artificial Intelligence Unit 3 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 3 Semester 3 MSc IT Part 2 Mumbai Univer...
 
Introduction to machine learning and model building using linear regression
Introduction to machine learning and model building using linear regressionIntroduction to machine learning and model building using linear regression
Introduction to machine learning and model building using linear regression
 
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
 
Ds for finance day 3
Ds for finance day 3Ds for finance day 3
Ds for finance day 3
 
A Friendly Introduction to Machine Learning
A Friendly Introduction to Machine LearningA Friendly Introduction to Machine Learning
A Friendly Introduction to Machine Learning
 
Machine Learning Applications in Credit Risk
Machine Learning Applications in Credit RiskMachine Learning Applications in Credit Risk
Machine Learning Applications in Credit Risk
 
Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
LearningKit.ppt
LearningKit.pptLearningKit.ppt
LearningKit.ppt
 
An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!
 
Machine Learning Unit 1 Semester 3 MSc IT Part 2 Mumbai University
Machine Learning Unit 1 Semester 3  MSc IT Part 2 Mumbai UniversityMachine Learning Unit 1 Semester 3  MSc IT Part 2 Mumbai University
Machine Learning Unit 1 Semester 3 MSc IT Part 2 Mumbai University
 

Ähnlich wie Explainable AI Workshop

Visual diagnostics for more effective machine learning
Visual diagnostics for more effective machine learningVisual diagnostics for more effective machine learning
Visual diagnostics for more effective machine learning
Benjamin Bengfort
 
Visual pattern recognition
Visual pattern recognitionVisual pattern recognition
Visual pattern recognition
Rushin Shah
 
Machine Learning Notes for beginners ,Step by step
Machine Learning Notes for beginners ,Step by stepMachine Learning Notes for beginners ,Step by step
Machine Learning Notes for beginners ,Step by step
SanjanaSaxena17
 

Ähnlich wie Explainable AI Workshop (20)

ML Workshop at SACON 2018
ML Workshop at SACON 2018ML Workshop at SACON 2018
ML Workshop at SACON 2018
 
Visual diagnostics for more effective machine learning
Visual diagnostics for more effective machine learningVisual diagnostics for more effective machine learning
Visual diagnostics for more effective machine learning
 
Visual pattern recognition
Visual pattern recognitionVisual pattern recognition
Visual pattern recognition
 
Software Verification with Abstraction-Based Methods
Software Verification with Abstraction-Based MethodsSoftware Verification with Abstraction-Based Methods
Software Verification with Abstraction-Based Methods
 
Practical Data Science Workshop - Recommendation Systems - Collaborative Filt...
Practical Data Science Workshop - Recommendation Systems - Collaborative Filt...Practical Data Science Workshop - Recommendation Systems - Collaborative Filt...
Practical Data Science Workshop - Recommendation Systems - Collaborative Filt...
 
Machine Learning Notes for beginners ,Step by step
Machine Learning Notes for beginners ,Step by stepMachine Learning Notes for beginners ,Step by step
Machine Learning Notes for beginners ,Step by step
 
Introduction to Datamining Concept and Techniques
Introduction to Datamining Concept and TechniquesIntroduction to Datamining Concept and Techniques
Introduction to Datamining Concept and Techniques
 
Visualizing Model Selection with Scikit-Yellowbrick: An Introduction to Devel...
Visualizing Model Selection with Scikit-Yellowbrick: An Introduction to Devel...Visualizing Model Selection with Scikit-Yellowbrick: An Introduction to Devel...
Visualizing Model Selection with Scikit-Yellowbrick: An Introduction to Devel...
 
Introduction of Feature Hashing
Introduction of Feature HashingIntroduction of Feature Hashing
Introduction of Feature Hashing
 
Dimension reduction techniques[Feature Selection]
Dimension reduction techniques[Feature Selection]Dimension reduction techniques[Feature Selection]
Dimension reduction techniques[Feature Selection]
 
Genetic Algorithm
Genetic AlgorithmGenetic Algorithm
Genetic Algorithm
 
Deep_Learning__INAF_baroncelli.pdf
Deep_Learning__INAF_baroncelli.pdfDeep_Learning__INAF_baroncelli.pdf
Deep_Learning__INAF_baroncelli.pdf
 
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017
 
Lab 2: Classification and Regression Prediction Models, training and testing ...
Lab 2: Classification and Regression Prediction Models, training and testing ...Lab 2: Classification and Regression Prediction Models, training and testing ...
Lab 2: Classification and Regression Prediction Models, training and testing ...
 
Ml10 dimensionality reduction-and_advanced_topics
Ml10 dimensionality reduction-and_advanced_topicsMl10 dimensionality reduction-and_advanced_topics
Ml10 dimensionality reduction-and_advanced_topics
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
ga-2.ppt
ga-2.pptga-2.ppt
ga-2.ppt
 
Mining attributes
Mining attributesMining attributes
Mining attributes
 
CSL0777-L07.pptx
CSL0777-L07.pptxCSL0777-L07.pptx
CSL0777-L07.pptx
 
ICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoTICMT 2016: Search-Based Model Transformations with MOMoT
ICMT 2016: Search-Based Model Transformations with MOMoT
 

Mehr von QuantUniversity

EU Artificial Intelligence Act 2024 passed !
EU Artificial Intelligence Act 2024 passed !EU Artificial Intelligence Act 2024 passed !
EU Artificial Intelligence Act 2024 passed !
QuantUniversity
 

Mehr von QuantUniversity (20)

EU Artificial Intelligence Act 2024 passed !
EU Artificial Intelligence Act 2024 passed !EU Artificial Intelligence Act 2024 passed !
EU Artificial Intelligence Act 2024 passed !
 
Managing-the-Risks-of-LLMs-in-FS-Industry-Roundtable-TruEra-QuantU.pdf
Managing-the-Risks-of-LLMs-in-FS-Industry-Roundtable-TruEra-QuantU.pdfManaging-the-Risks-of-LLMs-in-FS-Industry-Roundtable-TruEra-QuantU.pdf
Managing-the-Risks-of-LLMs-in-FS-Industry-Roundtable-TruEra-QuantU.pdf
 
PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALS
PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALSPYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALS
PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALS
 
Qu for India - QuantUniversity FundRaiser
Qu for India  - QuantUniversity FundRaiserQu for India  - QuantUniversity FundRaiser
Qu for India - QuantUniversity FundRaiser
 
Ml master class for CFA Dallas
Ml master class for CFA DallasMl master class for CFA Dallas
Ml master class for CFA Dallas
 
Algorithmic auditing 1.0
Algorithmic auditing 1.0Algorithmic auditing 1.0
Algorithmic auditing 1.0
 
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
Towards Fairer Datasets: Filtering and Balancing the Distribution of the Peop...
 
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...Machine Learning: Considerations for Fairly and Transparently Expanding Acces...
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...
 
Seeing what a gan cannot generate: paper review
Seeing what a gan cannot generate: paper reviewSeeing what a gan cannot generate: paper review
Seeing what a gan cannot generate: paper review
 
AI Explainability and Model Risk Management
AI Explainability and Model Risk ManagementAI Explainability and Model Risk Management
AI Explainability and Model Risk Management
 
Algorithmic auditing 1.0
Algorithmic auditing 1.0Algorithmic auditing 1.0
Algorithmic auditing 1.0
 
Machine Learning in Finance: 10 Things You Need to Know in 2021
Machine Learning in Finance: 10 Things You Need to Know in 2021Machine Learning in Finance: 10 Things You Need to Know in 2021
Machine Learning in Finance: 10 Things You Need to Know in 2021
 
Bayesian Portfolio Allocation
Bayesian Portfolio AllocationBayesian Portfolio Allocation
Bayesian Portfolio Allocation
 
The API Jungle
The API JungleThe API Jungle
The API Jungle
 
Responsible AI in Action
Responsible AI in ActionResponsible AI in Action
Responsible AI in Action
 
Qu speaker series 14: Synthetic Data Generation in Finance
Qu speaker series 14: Synthetic Data Generation in FinanceQu speaker series 14: Synthetic Data Generation in Finance
Qu speaker series 14: Synthetic Data Generation in Finance
 
Qwafafew meeting 5
Qwafafew meeting 5Qwafafew meeting 5
Qwafafew meeting 5
 
Qu speaker series:Ethical Use of AI in Financial Markets
Qu speaker series:Ethical Use of AI in Financial MarketsQu speaker series:Ethical Use of AI in Financial Markets
Qu speaker series:Ethical Use of AI in Financial Markets
 
Fintech in the Post-Covid Age
Fintech in the Post-Covid AgeFintech in the Post-Covid Age
Fintech in the Post-Covid Age
 
Ml master class northeastern university
Ml master class   northeastern universityMl master class   northeastern university
Ml master class northeastern university
 

Kürzlich hochgeladen

Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
gajnagarg
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men 🔝Ongole🔝 Escorts S...
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men  🔝Ongole🔝   Escorts S...➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men  🔝Ongole🔝   Escorts S...
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men 🔝Ongole🔝 Escorts S...
amitlee9823
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
amitlee9823
 
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men 🔝Sambalpur🔝 Esc...
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men  🔝Sambalpur🔝   Esc...➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men  🔝Sambalpur🔝   Esc...
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men 🔝Sambalpur🔝 Esc...
amitlee9823
 

Kürzlich hochgeladen (20)

VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24  Building Real-Time Pipelines With FLaNKDATA SUMMIT 24  Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men 🔝Ongole🔝 Escorts S...
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men  🔝Ongole🔝   Escorts S...➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men  🔝Ongole🔝   Escorts S...
➥🔝 7737669865 🔝▻ Ongole Call-girls in Women Seeking Men 🔝Ongole🔝 Escorts S...
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
 
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men 🔝Sambalpur🔝 Esc...
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men  🔝Sambalpur🔝   Esc...➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men  🔝Sambalpur🔝   Esc...
➥🔝 7737669865 🔝▻ Sambalpur Call-girls in Women Seeking Men 🔝Sambalpur🔝 Esc...
 

Explainable AI Workshop

  • 1. Qu Speaker Series Explainable AI Workshop Explaining by Removing: A Unified Framework for Model Explanation Ian Covert University of Washington 2020 Copyright QuantUniversity LLC. Hosted By: Sri Krishnamurthy, CFA, CAP sri@quantuniversity.com www.qu.academy 12/16/2020 Qu.Academy https://quspeakerseries18.splashthat.com/
  • 2. 2 QuantUniversity • Boston-based Data Science, Quant Finance and Machine Learning training and consulting advisory • Trained more than 1000 students in Quantitative methods, Data Science and Big Data Technologies using MATLAB, Python and R • Building a platform for AI and Machine Learning Exploration and Experimentation
  • 3. 3 For registration information, go to https://QuFallSchool.splashthat.com
  • 6. 6
  • 7. 7 Demos, slides and video available on QuAcademy Go to www.qu.academy 7
  • 8. Explaining by Removing: A Unified Framework for Model Explanation Ian Covert
  • 9. Ian Covert, Scott Lundberg, Su-In Lee. “Explaining by Removing: A Unified Framework for Model Explanation.” arXiv preprint:2011.14878 Our paper
  • 10. 1. Motivation 2. A unified framework 3. Demonstration 4. Why feature removal? 5. Are there “right” choices? Contents
  • 11. > Black-box models increasingly popular > Explainable AI increasingly important > Which methods should we rely on? Motivation 𝑓
  • 12. > SHAP, LIME, SAGE, Occlusion, DeepLift, SmoothGrad, Integrated Gradients, GradCAM, CXPlain, L2X, INVASE, Meaningful Perturbations, Extremal Perturbations, RISE, TCAV, Guided Backprop, Excitation Backprop, IME, QII, PredDiff, MIR, Permutation Tests, LRP, FIDO-CA, Masking Model, Expected Gradients, LossSHAP, Shapley Effects, MP2-G, Saliency Maps, PDPs, ICEs, TreeSHAP, … Example methods
  • 13. > Researchers have made significant progress > The field is fragmented > Growing very fast > Lacking discussion of underlying principles Is the field in a good place?
  • 14. Monolithic algorithms à interchangeable choices Goals of this talk A unifying theory that describes 20+ methods One key idea about how to explain ML models
  • 15. 1. Motivation 2. A unified framework 3. Demonstration 4. Why feature removal? 5. Are there “right” choices? Contents
  • 16. > Many methods implicitly simulate feature removal > Non-trivial operation, different approaches > Further differences in generating final “explanation” Explaining by removing
  • 21. > The model 𝒇 requires a specific set of features 𝒇(𝒙) for 𝒙 ∈ 𝓧 > Require a subset function 𝑭 that accepts a feature subset 𝑭(𝒙 𝑺) for 𝒙 ∈ 𝒳 and 𝑺 ⊆ 𝟏, 𝟐, … , 𝒅 1. Feature removal
  • 22. > Select a target quantity to explain § Individual prediction: 𝒗 𝒙 𝑺 = 𝑭 𝒙 𝑺 § Prediction loss: 𝒗 𝒙𝒚 𝑺 = − ℓ 𝑭 𝒙 𝑺 , 𝒚 § Dataset loss: 𝒗 𝑺 = − 𝔼 ℓ 𝑭 𝑿 𝑺 , 𝒀 2. Model behavior 𝑓
  • 23. > Every method has an underlying set function 𝒗 𝑺 3. Summary technique
  • 24. > Every method has an underlying set function 𝒗 𝑺 3. Summary technique
  • 25. > Every method has an underlying set function 𝒗 𝑺 3. Summary technique
  • 26. > Every method has an underlying set function 𝒗 𝑺 > Explanations provide a concise summary 3. Summary technique
  • 27. > Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅 Summary types
  • 28. > Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅 > E.g., remove individual Summary types −
  • 29. > Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅 > E.g., remove individual, include individual Summary types −
  • 30. > Feature attribution: output scores 𝒂 𝟏, 𝒂 𝟐, … , 𝒂 𝒅 > E.g., remove individual, include individual > Feature selection: output influential set 𝑺∗ ⊆ 𝟏, 𝟐, … , 𝒅 Summary types
  • 32. > Removal: default values > Behavior: individual prediction > Summary: fit linear model Example: LIME (2016)
  • 33. > Removal: marginalize out > Behavior: individual prediction (same as LIME) > Summary: Shapley value Example: SHAP (2017)
  • 34. > Removal: marginalize out (same as SHAP) > Behavior: dataset loss > Summary: Shapley value (same as SHAP) Example: SAGE (2020)
  • 35. > Removal: marginalize out (same as SAGE) > Behavior: dataset loss (same as SAGE) > Summary: remove individual Example: permutation test (2001) −
  • 36. > 20+ existing methods > Local and global > Feature attribution and feature selection A unifying framework
  • 37. A unifying framework Remove individual Include individual Mean when included Shapley value Linear model High value subset Low value subset Partitioned subsets Zeros Occlusion CXPlain RISE MM Default values LIME (images) Extend pixels MIR Blurring EP MP Generative model FIDO-CA Marginalize (replacement distribution) LIME (tabular) Marginalize (uniform) IME (2010) Marginalize (marginals product) QII Marginalize (marginal) Permutation test SHAP KernelSHAP Marginalize (conditional) PredDiff Conditional perm. test SHAP SAGE LossSHAP Shapley Effects Tree distribution TreeSHAP Missingness during training L2X INVASE Separate models Feature ablation Univariate predictors IME (2009) Shapley Net Effects Summary technique Featureremoval ∎ Prediction ∎ Prediction loss ∎ Mean prediction loss ∎ Dataset loss ∎ Dataset loss (output)Model behavior Feature attribution Feature selection > Method “space” > Neighboring methods > Unique methods, new methods
  • 38. 1. Motivation 2. A unified framework 3. Demonstration 4. Why feature removal? 5. Are there “right” choices? Contents
  • 39. > GitHub: https://github.com/iancovert/removal-explanations > Simple implementation of many methods > Focus on interchangeable choices Demonstration
  • 40. Summary > A new class of methods based on feature removal > Each method is specified by three choices > Framework offers a great degree of flexibility Removal-based explanations
  • 41. 1. Is feature removal a smart approach to model explanation? 2. Are there “right” choices for each dimension? Key questions
  • 42. 1. Motivation 2. A unified framework 3. Demonstration 4. Why feature removal? 5. Are there “right” choices? Contents
  • 43. > Intuitive to many research groups > Feature removal is a form of counterfactual reasoning > Undo act of observing information (rather than changing what was observed) > Removal is anchored in psychology (subtractive counterfactual) and philosophy (method of difference) Why feature removal?
  • 44. > Counterfactuals change aspects of a situation (observation of feature values) > Can understand models by changing inputs > Often complicated to explore > Feature removal gives a more practical way to explore and summarize functions Counterfactual reasoning
  • 45. 1. Motivation 2. A unified framework 3. Demonstration 4. Why feature removal? 5. Are there “right” choices? Contents
  • 46. “Right” choices? > Methods determined by three choices > Every method has something to offer > Conceptual and computational trade-offs
  • 47. > Marginalizing out features with their conditional distribution > Difficult to implement, but many approximations > Yields information-theoretic explanations Feature removal strategy
  • 48. > Intuitively (Chest X-Ray) > How should a doctor interpret this? > Mathematically: 𝑭 𝒙 𝑺 = 𝔼 𝒇 𝑿 𝑿 𝑺 = 𝒙 𝑺 = ∫ 𝒑 𝒙(𝑺 𝒙 𝑺 𝒇(𝒙 𝑺, 𝒙(𝑺) Conditional distribution removal
  • 50. > Any choice provides valuable information > Range of perspectives > Depends on use-case Model behavior
  • 51. > Precedent in cooperative game theory > Many potential desirable properties > Shapley value satisfies most 𝝓𝒊 𝒗 = 𝟏 𝒅 < 𝑺⊆𝑫- 𝒅 − 𝟏 𝑺 .𝟏 𝒗 𝑺 ∪ 𝒊 − 𝒗 𝑺 Summary technique
  • 53. 1. Motivation 2. A unified framework 3. Why feature removal? 4. Demonstration 5. Are there “right” choices? 6. Conclusion + questions Contents
  • 54. > Presented a new perspective for understanding explainability tools > Developed rigorous foundations > Aim to inform practitioners, guide researchers Concluding thoughts
  • 56. 56 Instructions for the Lab: 1. Go to https://academy.qusandbox.com/#/register and register using the code: "QUFALLSCHOOL"
  • 57. Thank you! Sri Krishnamurthy, CFA, CAP Founder and CEO QuantUniversity LLC. srikrishnamurthy www.QuantUniversity.com Contact Information, data and drawings embodied in this presentation are strictly a property of QuantUniversity LLC. and shall not be distributed or used in any other publication without the prior written consent of QuantUniversity LLC. 57