SlideShare ist ein Scribd-Unternehmen logo
1 von 58
Downloaden Sie, um offline zu lesen
Manipulating and Measuring Model Interpretability
Microsoft Research NYC
Forough Poursabzi-
Sangdeh
Dan Goldstein Jake Hofman Jenn Wortman
Vaughan
Hanna Wallach
u = k(x, u)
INTERPRETABLE MACHINE LEARNING
u = k(x, u)
e.g., generalized additive models
Lou et al. 2012 and 2013
Simple models
INTERPRETABLE MACHINE LEARNING
u = k(x, u)
e.g., LIME
Ribiero et al. 2016
Post-hoc explanations
e.g., generalized additive models
Lou et al. 2012 and 2013
Simple models
INTERPRETABLE MACHINE LEARNING
INTERPRETABILITY?
u = k(x, u)
• What makes a model or explanation interpretable?
DIFFERENT SCENARIOS, DIFFERENT PEOPLE, DIFFERENT NEEDS
u = k(x, u)
Explain a
prediction
Understand
model
Make better
decisions
Debug
model
De-bias
model
Inspire trust
CEOs Approach A
Data
scientists
Approach C
Laypeople
Regulators Approach B
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
number of features
linearity
black-box vs. clear
visualizations
types of features
…
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
number of features
linearity
black-box vs. clear
visualizations
types of features
… …
trust
ability to debug
ability to simulate
ability to explain
ability to detect mistakes
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
number of features
linearity
black-box vs. clear
visualizations
types of features
…
properties of model and
system design
…
trust
ability to debug
ability to simulate
ability to explain
ability to detect mistakes
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
number of features
linearity
black-box vs. clear
visualizations
types of features
…
properties of human
behavior
properties of model and
system design
…
trust
ability to debug
ability to simulate
ability to explain
ability to detect mistakes
Interpretability
INTERPRETABILITY AS A LATENT PROPERTY
number of features
linearity
black-box vs. clear
visualizations
types of features
…
properties of human
behavior
We need interdisciplinary approaches
properties of model and
system design
…
trust
ability to debug
ability to simulate
ability to explain
ability to detect mistakes
Interpretability
FOCUS ON LAYPEOPLE
number of features
linearity
black-box vs. clear
visualizations
types of features
…
properties of human
behavior
Randomized human-subject experiments
properties of model and
system design
…
trust
ability to debug
ability to simulate
ability to explain
ability to detect mistakes
USER EXPERIMENT, PREDICTIVE TASK
u = k(x, u)
• Predict the price of apartments in NYC with the help of a model
EXPERIMENTAL CONDITIONS
EXPERIMENTAL CONDITIONS
EXPERIMENTAL CONDITIONS
EXPERIMENTAL CONDITIONS
EXPERIMENTAL CONDITIONS
CLEAR-2 feature BB-2 feature
CLEAR-8 feature BB-8 feature
TIGHTLY CONTROLLED EXPERIMENTS
CLEAR-2 feature BB-2 feature
CLEAR-8 feature BB-8 feature
TIGHTLY CONTROLLED EXPERIMENTS
CLEAR-2 feature BB-2 feature
CLEAR-8 feature BB-8 feature
TIGHTLY CONTROLLED EXPERIMENTS
CLEAR-2 feature BB-2 feature
CLEAR-8 feature BB-8 feature
USER INTERFACE AND INTERACTIONS
u = k(x, u)
• Training phase: participants get familiar with the model
• Testing phase step 1: simulate the model’s prediction
Simulate the model
USER INTERFACE AND INTERACTIONS
u = k(x, u)
• Testing phase step 2: observe the model’s prediction and guess the price
Predict actual selling price
PRE-REGISTERED HYPOTHESES
u = k(x, u)
• CLEAR-2 feature will be easiest for participants to simulate
• Participants will trust CLEAR-2 feature more than BB-8 feature
• Participants’ behaviors will vary when they see unusual examples where the model makes
inaccurate predictions
https://aspredicted.org/xy5s6.pdf
SIMULATION ERROR
u = k(x, u)
CLEAR-2 feature will be easiest for participants to simulate
SIMULATION ERROR
u = k(x, u)
CLEAR-2 feature will be easiest for participants to simulate
m
$um
SIMULATION ERROR
u = k(x, u)
CLEAR-2 feature will be easiest for participants to simulate
Simulation error
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$100k
$200k
Meansimulationerror
m
$um
SIMULATION ERROR
u = k(x, u)
CLEAR-2 feature will be easiest for participants to simulate
Simulation error
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$100k
$200k
Meansimulationerror
m
$um
TRUST (DEVIATION FROM THE MODEL)
Participants will trust CLEAR-2 feature more than BB-8 feature
TRUST (DEVIATION FROM THE MODEL)
Participants will trust CLEAR-2 feature more than BB-8 feature
m
$ua
Deviation
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$50k
$100k
$150k
Meandeviationfromthemodel
TRUST (DEVIATION FROM THE MODEL)
Participants will trust CLEAR-2 feature more than BB-8 feature
m
$ua
Deviation
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$50k
$100k
$150k
Meandeviationfromthemodel
TRUST (DEVIATION FROM THE MODEL)
Participants will trust CLEAR-2 feature more than BB-8 feature
m
$ua
WEIRD APARTMENT
u = k(x, u)
DETECTION OF MISTAKES
Participants’ behaviors will vary when they see unusual examples where the model makes
inaccurate predictions
DETECTION OF MISTAKES
Participants’ behaviors will vary when they see unusual examples where the model makes
inaccurate predictions
m
$ua
DETECTION OF MISTAKES
Participants’ behaviors will vary when they see unusual examples where the model makes
inaccurate predictions
Apartment 12: 1 bed, 3 bath
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$50k
$100k
$150k
$200k
$250k
$300k
Meandeviationfromthemodel
forapartment12 m
$ua
DETECTION OF MISTAKES
Participants’ behaviors will vary when they see unusual examples where the model makes
inaccurate predictions
Apartment 12: 1 bed, 3 bath
CLEAR−2 CLEAR−8 BB−2 BB−8
$0k
$50k
$100k
$150k
$200k
$250k
$300k
Meandeviationfromthemodel
forapartment12 m
$ua
When participants see unusual examples, they are less likely to correct inaccurate
predictions made by clear models than black-box models
WHAT IS UP WITH THIS?
CONJECTURE: VISUAL OVERLOAD
CONJECTURE: VISUAL OVERLOAD
CONJECTURE: ANCHORING EFFECT
CONJECTURE: ANCHORING EFFECT
User’s simulation of the model’s prediction
EXPLICIT ATTENTION CHECK
USER INTERFACE AND INTERACTIONS
u = k(x, u)
• We remove potential anchors
PRE-REGISTERED HYPOTHESES
u = k(x, u)
• Explicit attention checks on unusual inputs will affect participants’ abilities in detecting
model’s mistakes
• Model transparency affects participants’ abilities in detecting model’s mistakes, both with
and without attention checks
https://aspredicted.org/5xy8y.pdf
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• Attention checks improve users’ ability to correct model’s mistakes
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• Attention checks improve users’ ability to correct model’s mistakes
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• Attention checks improve users’ ability to correct model’s mistakes
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• Attention checks improve users’ ability to correct model’s mistakes
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
• With attention checks, there is no difference between clear and black-box
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantpredictio
Model's prediction CLEAR BB
DETECTION OF MISTAKES
• Attention checks improve users’ ability to correct model’s mistakes
• No attention checks: clear models lower users’ ability to correct model’s
mistakes
• With attention checks, there is no difference between clear and black-box
Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft
No attention
check
With attention
check
No attention
check
With attention
check
$0M
$0.5M
$1M
$1.5M
Meanparticipantprediction
Model's prediction CLEAR BB
SUMMARY OF RESULTS
u = k(x, u)
• A clear model with a small number of features is easier for participants to simulate
- People have a better understanding of simple and transparent models
• No significant difference in participants’ trust in the model
- Contrary to intuition, people do not necessarily trust simple and transparent models
more
• Participants were less able to correct inaccurate predictions of a clear model than a black-
box model
- Too much transparency can be harmful
- Design implications (e.g., highlighting unusual inputs, display model internals on
demand)
• Interpretability is not a purely computational problem
- We need interdisciplinary research to understand interpretability
• Our surprising results underscore that interpretability research is much more complicated
- We need more empirical studies
- Other scenarios, domains, models, factors, outcomes
TAKEAWAYS
u = k(x, u)
https://csel.cs.colorado.edu/~fopo5620/
forough.poursabzi@microsoft.com
Thanks!

Weitere ähnliche Inhalte

Ähnlich wie Manipulating and measuring model interpretability

[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
YONG ZHENG
 
Personalised Recommendations in E-Commerce
Personalised Recommendations in E-CommercePersonalised Recommendations in E-Commerce
Personalised Recommendations in E-Commerce
Wing Yung Chan
 

Ähnlich wie Manipulating and measuring model interpretability (20)

MUMS: Transition & SPUQ Workshop - Stochastic Simulators: Issues, Methods, Un...
MUMS: Transition & SPUQ Workshop - Stochastic Simulators: Issues, Methods, Un...MUMS: Transition & SPUQ Workshop - Stochastic Simulators: Issues, Methods, Un...
MUMS: Transition & SPUQ Workshop - Stochastic Simulators: Issues, Methods, Un...
 
Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )
 
Causal inference-for-profit | Dan McKinley | DN18
Causal inference-for-profit | Dan McKinley | DN18Causal inference-for-profit | Dan McKinley | DN18
Causal inference-for-profit | Dan McKinley | DN18
 
DN18 | A/B Testing: Lessons Learned | Dan McKinley | Mailchimp
DN18 | A/B Testing: Lessons Learned | Dan McKinley | MailchimpDN18 | A/B Testing: Lessons Learned | Dan McKinley | Mailchimp
DN18 | A/B Testing: Lessons Learned | Dan McKinley | Mailchimp
 
FairBench: A Fairness Assessment Framework
FairBench: A Fairness Assessment FrameworkFairBench: A Fairness Assessment Framework
FairBench: A Fairness Assessment Framework
 
UXD lesson 1 - Intro To UX
UXD lesson 1 - Intro To UXUXD lesson 1 - Intro To UX
UXD lesson 1 - Intro To UX
 
Engine90 crawford-decision-making (1)
Engine90 crawford-decision-making (1)Engine90 crawford-decision-making (1)
Engine90 crawford-decision-making (1)
 
Avi-newmans_fast_community_detection.pptx
Avi-newmans_fast_community_detection.pptxAvi-newmans_fast_community_detection.pptx
Avi-newmans_fast_community_detection.pptx
 
HOP-Rec_RecSys18
HOP-Rec_RecSys18HOP-Rec_RecSys18
HOP-Rec_RecSys18
 
[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
[SAC2014]Splitting Approaches for Context-Aware Recommendation: An Empirical ...
 
House price prediction
House price predictionHouse price prediction
House price prediction
 
How to focus - design your new app in 60 minutes!
How to focus - design your new app in 60 minutes!How to focus - design your new app in 60 minutes!
How to focus - design your new app in 60 minutes!
 
BSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, EvaluationsBSSML17 - Introduction, Models, Evaluations
BSSML17 - Introduction, Models, Evaluations
 
Personalised Recommendations in E-Commerce
Personalised Recommendations in E-CommercePersonalised Recommendations in E-Commerce
Personalised Recommendations in E-Commerce
 
Design of Engineering Experiments Part 5
Design of Engineering Experiments Part 5Design of Engineering Experiments Part 5
Design of Engineering Experiments Part 5
 
Data Science Popup Austin: Predicting Customer Behavior & Enhancing Customer ...
Data Science Popup Austin: Predicting Customer Behavior & Enhancing Customer ...Data Science Popup Austin: Predicting Customer Behavior & Enhancing Customer ...
Data Science Popup Austin: Predicting Customer Behavior & Enhancing Customer ...
 
Study on Application of Ensemble learning on Credit Scoring
Study on Application of Ensemble learning on Credit ScoringStudy on Application of Ensemble learning on Credit Scoring
Study on Application of Ensemble learning on Credit Scoring
 
Using Diversity for Automated Boundary Value Testing
Using Diversity for Automated Boundary Value TestingUsing Diversity for Automated Boundary Value Testing
Using Diversity for Automated Boundary Value Testing
 
Explainable ai data_riders_2020-11-18
Explainable ai data_riders_2020-11-18Explainable ai data_riders_2020-11-18
Explainable ai data_riders_2020-11-18
 
Spc training
Spc training Spc training
Spc training
 

Mehr von MLconf

Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
MLconf
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
MLconf
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
MLconf
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
MLconf
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
MLconf
 

Mehr von MLconf (20)

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious Experience
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the Cheap
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data Collection
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of ML
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
 
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to code
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better Software
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime Changes
 

Kürzlich hochgeladen

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 

Kürzlich hochgeladen (20)

08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 

Manipulating and measuring model interpretability

  • 1. Manipulating and Measuring Model Interpretability Microsoft Research NYC Forough Poursabzi- Sangdeh Dan Goldstein Jake Hofman Jenn Wortman Vaughan Hanna Wallach
  • 2. u = k(x, u) INTERPRETABLE MACHINE LEARNING
  • 3. u = k(x, u) e.g., generalized additive models Lou et al. 2012 and 2013 Simple models INTERPRETABLE MACHINE LEARNING
  • 4. u = k(x, u) e.g., LIME Ribiero et al. 2016 Post-hoc explanations e.g., generalized additive models Lou et al. 2012 and 2013 Simple models INTERPRETABLE MACHINE LEARNING
  • 5. INTERPRETABILITY? u = k(x, u) • What makes a model or explanation interpretable?
  • 6. DIFFERENT SCENARIOS, DIFFERENT PEOPLE, DIFFERENT NEEDS u = k(x, u) Explain a prediction Understand model Make better decisions Debug model De-bias model Inspire trust CEOs Approach A Data scientists Approach C Laypeople Regulators Approach B
  • 8. Interpretability INTERPRETABILITY AS A LATENT PROPERTY number of features linearity black-box vs. clear visualizations types of features …
  • 9. Interpretability INTERPRETABILITY AS A LATENT PROPERTY number of features linearity black-box vs. clear visualizations types of features … … trust ability to debug ability to simulate ability to explain ability to detect mistakes
  • 10. Interpretability INTERPRETABILITY AS A LATENT PROPERTY number of features linearity black-box vs. clear visualizations types of features … properties of model and system design … trust ability to debug ability to simulate ability to explain ability to detect mistakes
  • 11. Interpretability INTERPRETABILITY AS A LATENT PROPERTY number of features linearity black-box vs. clear visualizations types of features … properties of human behavior properties of model and system design … trust ability to debug ability to simulate ability to explain ability to detect mistakes
  • 12. Interpretability INTERPRETABILITY AS A LATENT PROPERTY number of features linearity black-box vs. clear visualizations types of features … properties of human behavior We need interdisciplinary approaches properties of model and system design … trust ability to debug ability to simulate ability to explain ability to detect mistakes
  • 13. Interpretability FOCUS ON LAYPEOPLE number of features linearity black-box vs. clear visualizations types of features … properties of human behavior Randomized human-subject experiments properties of model and system design … trust ability to debug ability to simulate ability to explain ability to detect mistakes
  • 14. USER EXPERIMENT, PREDICTIVE TASK u = k(x, u) • Predict the price of apartments in NYC with the help of a model
  • 19. EXPERIMENTAL CONDITIONS CLEAR-2 feature BB-2 feature CLEAR-8 feature BB-8 feature
  • 20. TIGHTLY CONTROLLED EXPERIMENTS CLEAR-2 feature BB-2 feature CLEAR-8 feature BB-8 feature
  • 21. TIGHTLY CONTROLLED EXPERIMENTS CLEAR-2 feature BB-2 feature CLEAR-8 feature BB-8 feature
  • 22. TIGHTLY CONTROLLED EXPERIMENTS CLEAR-2 feature BB-2 feature CLEAR-8 feature BB-8 feature
  • 23. USER INTERFACE AND INTERACTIONS u = k(x, u) • Training phase: participants get familiar with the model • Testing phase step 1: simulate the model’s prediction Simulate the model
  • 24. USER INTERFACE AND INTERACTIONS u = k(x, u) • Testing phase step 2: observe the model’s prediction and guess the price Predict actual selling price
  • 25. PRE-REGISTERED HYPOTHESES u = k(x, u) • CLEAR-2 feature will be easiest for participants to simulate • Participants will trust CLEAR-2 feature more than BB-8 feature • Participants’ behaviors will vary when they see unusual examples where the model makes inaccurate predictions https://aspredicted.org/xy5s6.pdf
  • 26. SIMULATION ERROR u = k(x, u) CLEAR-2 feature will be easiest for participants to simulate
  • 27. SIMULATION ERROR u = k(x, u) CLEAR-2 feature will be easiest for participants to simulate m $um
  • 28. SIMULATION ERROR u = k(x, u) CLEAR-2 feature will be easiest for participants to simulate Simulation error CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $100k $200k Meansimulationerror m $um
  • 29. SIMULATION ERROR u = k(x, u) CLEAR-2 feature will be easiest for participants to simulate Simulation error CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $100k $200k Meansimulationerror m $um
  • 30. TRUST (DEVIATION FROM THE MODEL) Participants will trust CLEAR-2 feature more than BB-8 feature
  • 31. TRUST (DEVIATION FROM THE MODEL) Participants will trust CLEAR-2 feature more than BB-8 feature m $ua
  • 32. Deviation CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $50k $100k $150k Meandeviationfromthemodel TRUST (DEVIATION FROM THE MODEL) Participants will trust CLEAR-2 feature more than BB-8 feature m $ua
  • 33. Deviation CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $50k $100k $150k Meandeviationfromthemodel TRUST (DEVIATION FROM THE MODEL) Participants will trust CLEAR-2 feature more than BB-8 feature m $ua
  • 35. DETECTION OF MISTAKES Participants’ behaviors will vary when they see unusual examples where the model makes inaccurate predictions
  • 36. DETECTION OF MISTAKES Participants’ behaviors will vary when they see unusual examples where the model makes inaccurate predictions m $ua
  • 37. DETECTION OF MISTAKES Participants’ behaviors will vary when they see unusual examples where the model makes inaccurate predictions Apartment 12: 1 bed, 3 bath CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $50k $100k $150k $200k $250k $300k Meandeviationfromthemodel forapartment12 m $ua
  • 38. DETECTION OF MISTAKES Participants’ behaviors will vary when they see unusual examples where the model makes inaccurate predictions Apartment 12: 1 bed, 3 bath CLEAR−2 CLEAR−8 BB−2 BB−8 $0k $50k $100k $150k $200k $250k $300k Meandeviationfromthemodel forapartment12 m $ua When participants see unusual examples, they are less likely to correct inaccurate predictions made by clear models than black-box models
  • 39. WHAT IS UP WITH THIS?
  • 43. CONJECTURE: ANCHORING EFFECT User’s simulation of the model’s prediction
  • 45. USER INTERFACE AND INTERACTIONS u = k(x, u) • We remove potential anchors
  • 46. PRE-REGISTERED HYPOTHESES u = k(x, u) • Explicit attention checks on unusual inputs will affect participants’ abilities in detecting model’s mistakes • Model transparency affects participants’ abilities in detecting model’s mistakes, both with and without attention checks https://aspredicted.org/5xy8y.pdf
  • 47. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 48. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 49. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 50. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 51. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • Attention checks improve users’ ability to correct model’s mistakes • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 52. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • Attention checks improve users’ ability to correct model’s mistakes • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 53. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • Attention checks improve users’ ability to correct model’s mistakes • No attention checks: clear models lower users’ ability to correct model’s mistakes Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 54. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • Attention checks improve users’ ability to correct model’s mistakes • No attention checks: clear models lower users’ ability to correct model’s mistakes • With attention checks, there is no difference between clear and black-box Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 55. Apartment 6: 1 bed, 3 bath, 726 sq ft Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantpredictio Model's prediction CLEAR BB DETECTION OF MISTAKES • Attention checks improve users’ ability to correct model’s mistakes • No attention checks: clear models lower users’ ability to correct model’s mistakes • With attention checks, there is no difference between clear and black-box Apartment 6: 1 bed, 3 bath Apartment 8: 1 bed, 3 bath, 350 sq ft No attention check With attention check No attention check With attention check $0M $0.5M $1M $1.5M Meanparticipantprediction Model's prediction CLEAR BB
  • 56. SUMMARY OF RESULTS u = k(x, u) • A clear model with a small number of features is easier for participants to simulate - People have a better understanding of simple and transparent models • No significant difference in participants’ trust in the model - Contrary to intuition, people do not necessarily trust simple and transparent models more • Participants were less able to correct inaccurate predictions of a clear model than a black- box model - Too much transparency can be harmful - Design implications (e.g., highlighting unusual inputs, display model internals on demand)
  • 57. • Interpretability is not a purely computational problem - We need interdisciplinary research to understand interpretability • Our surprising results underscore that interpretability research is much more complicated - We need more empirical studies - Other scenarios, domains, models, factors, outcomes TAKEAWAYS
  • 58. u = k(x, u) https://csel.cs.colorado.edu/~fopo5620/ forough.poursabzi@microsoft.com Thanks!