WiTS Virtual - Digital Discrimination: Cognitive Bias in Machine Learning

Digital Discrimination Resources

My team’s work:
http://ibm.biz/codait-trusted-ai
https://developer.ibm.com/blogs/ibm-and-lfai-move-forward-on-trustworthy-and-responsible-ai/
https://www.ibm.com/blogs/policy/facial-recognition-sunset-racial-justice-reforms/

Criminal Recidivism Scoring
http://www.equivant.com/solutions/inmate-classification
https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing

Gender Shades/Algorithmic Justice League
http://gendershades.org/
http://www.aies-conference.com/wp-content/uploads/2019/01/AIES-19_paper_223.pdf
https://www.youtube.com/watch?v=Af2VmR-iGkY
https://www.ajlunited.org/fight
https://www.npr.org/2020/06/24/882683463/the-computer-got-it-wrong-how-facial-recognition-led-to-a-false-arrest-in-michig

Ethics in Computer Science
https://www.nytimes.com/2018/02/12/business/computer-science-ethics-courses.html
https://twitter.com/Neurosarda/status/1084198368526680064

Pinterest Skin Tone Search
https://www.engadget.com/2019/01/24/pinterest-skin-tone-search-diversity/

Industry/Government Definitions of Trustworthy AI
https://ec.europa.eu/digital-single-market/en/news/ethics-guidelines-trustworthy-ai
https://wiki.lfai.foundation/display/DL/Trusted+AI+Committee

Transcript

1. Digital Discrimination: Cognitive Bias in Machine Learning Maureen McElaney, Program Manager IBM Quantum July 28, 2020
2. About Me... 2
3. Digital Discrimination: Cognitive Bias in Machine Learning Tweet at me! @Mo_Mack
4. 4 Agenda • Examples of Bias in Machine Learning. • Solutions to combat unwanted bias. • Tools to combat unwanted bias. • Resources and how to get involved.
5. A cognitive bias is a systematic pattern of deviation from norm or rationality in judgment. People make decisions given their limited resources. Wilke A. and Mata R. (2012) “Cognitive Bias”, Clarkson University @Mo_Mack
6. Examples of bias in machine learning. @Mo_Mack
7. @Mo_Mack NorthPointe’s COMPAS Algorithm Image Credit: #WOCinTech
8. Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing May 2016 - Northpointe’s COMPAS Algorithm http://www.equivant.com/solutions/inmate- classification
9. May 2016 - Northpointe’s COMPAS Algorithm http://www.equivant.com/solutions/inmate- classification Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
10. May 2016 - Northpointe’s COMPAS Algorithm http://www.equivant.com/solutions/inmate- classification Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
11. May 2016 - Northpointe’s COMPAS Algorithm http://www.equivant.com/solutions/inmate- classification Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
12. Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing Black Defendant’s Risk Scores
13. Source: https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing White Defendant’s Risk Scores
14. @Mo_Mack BLACK VS. WHITE DEFENDANTS ◦ Falsely labeled black defendants as likely of future crime at twice the rate as white defendants. ◦ White defendants mislabeled as low risk more than black defendants ◦ Pegged Black defendants 77% more likely to be at risk of committing future violent crime
16. @Mo_Mack Gender Shades Project February 2018 Image Credit: #WOCinTech
17. http://gendershades.org/
18. “If we fail to make ethical and inclusive artificial intelligence we risk losing gains made in civil rights and gender equity under the guise of machine neutrality.” - Joy Boulamwini @jovialjoy
19. http://www.aies-conference.com/wp-content/uploads/2019/01/AIES-19_paper_223.pdf
20. @Mo_Mack https://www.youtube.com/watch?v=Af2VmR-iGkY
21. @Mo_Mack
23. 23 Agenda • Examples of Bias in Machine Learning. • Solutions to combat unwanted bias. • Tools to combat unwanted bias. • Resources and how to get involved.
24. Solutions? What can we do to combat bias in AI? @Mo_Mack
25. @Mo_Mack EDUCATION IS KEY Image Credit: #WOCinTech
26. https://www.nytimes.com/2018/02/12/business/computer-science- ethics-courses.html
27. Questions posed to students in these courses... Is the technology fair? How do you make sure that the data is not biased? Should machines be judging humans? @Mo_Mack
28. https://twitter.com/Neurosarda/status/1084198368526680064
29. FIX THE PIPELINE? @Mo_Mack Image Credit: #WOCinTech
30. “Cognitive bias in machine learning is human bias on steroids.” 30 - Rediet Abebe @red_abebe
31. https://twitter.com/MatthewBParksSr/status/1133435312921874432
32. January 2019 - New Search Feature on... https://www.pinterest.com Source: https://www.engadget.com/2019/01/24/pinterest-skin-tone-search-diversity/
33. “By combining the latest in machine learning and inclusive product development, we're able to directly respond to Pinner feedback and build a more useful product.” 33 - Candice Morgan @Candice_MMorgan
34. @Mo_Mack National and Industry Standards Image Credit: #WOCinTech
35. EU Ethics Guidelines for Trustworthy Artificial Intelligence According to the Guidelines, trustworthy AI should be: (1) lawful - respecting all applicable laws and regulations (2) ethical - respecting ethical principles and values (3) robust - both from a technical perspective while taking into account its social environment Source: https://ec.europa.eu/digital-single-market/en/news/ethics-guidelines-trustworthy-ai
36. #1 - Human agency and oversight. #2 - Technical robustness and safety. #3 - Privacy and data governance. #4 - Transparency . @Mo_Mack #5 - Diversity, non- discrimination and fairness. #6 - Societal and environmental well-being. #7 - Accountability
37. https://wiki.lfai.foundation/display/DL/Trusted+AI+Committee
38. 38 Agenda • Examples of Bias in Machine Learning. • Solutions to combat unwanted bias. • Tools to combat unwanted bias. • Resources and how to get involved.
39. @Mo_Mack TOOLS TO COMBAT BIAS Image Credit: #WOCinTech
40. Tool #1: AI Fairness 360 Toolkit Open Source Library @Mo_Mack
41. http://aif360.mybluemix.net/
42. http://aif360.mybluemix.net/
43. Machine Learning Pipeline In- Processing Pre- Processing Post- Processing Modifying the training data. Modifying the learning algorithm. Modifying the predictions (or outcomes.)
44. http://aif360.mybluemix.net/ Demos
45. https://github.com/IBM/AIF360 AI Fairness 360 Toolkit Public Repo
46. Tool #2: AI Explainability 360 Toolkit Open Source Library
47. AIX360 toolkit is an open-source library to help explain AI and machine learning models and their predictions. This includes three classes of algorithms: local post-hoc, global post-hoc, and directly interpretable explainers for models that use image, text, and structured/tabular data. The AI Explainability360 Python package includes a comprehensive set of explainers, both at global and local level. Toolbox Local post-hoc Global post-hoc Directly interpretable AI Explainability 360 ↳ (AIX360) https://github.com/IBM/AIX360 http://aix360.mybluemix.net THINK 2020 / © 2020 IBM Corporation
48. Tackling different ways to explain Selected 2018 explainability innovations from IBM Research GLOBAL, POST-HOC Improving Simple Models with Confidence Profiles NEURIPS 2018 LOCAL, POST-HOC Explanations Based on the Missing: Towards Contrastive Explanations with Pertinent Negatives NEURIPS 2018 GLOBAL, DIRECTLY INTERPRETABLE Boolean Decision Rules via Column Generation NIPS 2018 Variational Inference of Disentangled Latent Concepts from Unlabeled Observations ICLR 2018 INTERACTIVE MODEL VISUALIZATION Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models IEEE VAST 2018 LOCAL, DIRECTLY INTERPRETABLE TED: Teaching AI to Explain its Decisions AIES 2019 THINK 2020 / © 2020 IBM Corporation
49. Three dimensions of explainability One explanation does not fit all: There are many ways to explain things directly interpretable The oldest AI formats, such as decision rule sets, decision trees, and decision tables are simple enough for people to understand. Supervised learning of these models is directly interpretable. vs. post hoc interpretation Start with a black box model and probe into it with a companion model to create interpretations. The black box model continues to provide the actual prediction while interpretation improve human interactions. global (model-level) Show the entire predictive model to the user to help them understand it (e.g. a small decision tree, whether obtained directly or in a post hoc manner). vs. local (instance-level) Only show the explanations associated with individual predictions (i.e. what was it about the features of this particular person that made her loan denied). static The interpretation is simply presented to the user. vs. interactive (visual analytics) The user can interact with interpretation.
50. Data explanation • ProtoDash (Gurumoorthy et al., 2019) • Disentangled Inferred Prior VAE (Kumar et al., 2018) Supported explainability algorithms Local post-hoc explanation • ProtoDash (Gurumoorthy et al., 2019) • Contrastive Explanations Method (Dhurandhar et al., 2018) • Contrastive Explanations Method with Monotonic Attribute Functions (Luss et al., 2019) • LIME (Ribeiro et al. 2016, Github) • SHAP (Lundberg, et al. 2017, Github) Local direct explanation • Teaching AI to Explain its Decisions (Hind et al., 2019) Global direct explanation • Boolean Decision Rules via Column Generation (Light Edition) (Dash et al., 2018) • Generalized Linear Rule Models (Wei et al., 2019) Global post-hoc explanation • ProfWeight (Dhurandhar et al., 2018) Supported explainability metrics • Faithfulness (Alvarez-Melis and Jaakkola, 2018) • Monotonicity (Luss et al., 2019)
51. Explain how AI arrived at a prediction • Uses contrastive techniques to explain model behavior in the vicinity of the target data point. • Identifies feature weighting of most and least important features • Displays factors that influence a prediction in simple terms. • Explanation in terms of the top-K features which played a key role in the prediction. E.g., The loan was rejected because: (1) Credit score=average, (2) Loan Amount>$2M and (3) Area=Downtown. Explainability THINK 2020 / © 2020 IBM Corporation
52. Prediction: Partially Granted 1 2 3 4 5 6 7 8 9 Input Data Point PP PN Partially Approved Approved Most Frequent Least Frequent Number of Married Years Contrastive Explanation: • PP: If Number of married years was 7 and salary was in the range $190-210K, then outcome would have changed to Loan=Approved • PN: Even if Number of married years = 3 and salary was in the range $110-130K, outcome would have been Loan=Partially Granted [90, 110] [70, 90] [110,13 0] Most Frequent Least Frequent Input Data Point PP Salary PN Partially Approved Approved [>210] [130,15 0] [150,17 0] [170,19 0] [190,21 0] THINK 2020 / © 2020 IBM Corporation
53. https://github.com/IBM/AIX360 AI Explainability 360 Toolkit Public Repo
54. IBM donates "Trusted AI" projects to Linux Foundation AI Source: https://www.zdnet.com/article/ibm-donates-trusted-ai-projects-to-linux-foundation-ai/
55. Tool #3: Model Asset eXchange Open Source Pre-Trained Deep Learning Models
56. Step 1: Find a model ...that does what you need ...that is free to use ...that is performant enough
57. Step 2: Get the code Is there a good implementation available? ...that does what you need ...that is free to use ...that is performant enough
58. Step 3: Verify the model ◦ Does it do what you need? ◦ Is it free to use (license)? ◦ Is it performant enough? ◦ Accuracy?
59. Step 4: Train the model
60. Step 4: Train the model
61. Step 5: Deploy your model ◦ Adjust inference code (or write from scratch) ◦ Package inference code, model code, and pre-trained weights together ◦ Deploy your package
62. Step 6: Consume your model
63. Model Asset Exchange The Model Asset Exchange (MAX) is a one stop shop for developers/data scientists to find and use free and open source deep learning models ibm.biz/model-exchange
64. ibm.biz/model-exchange
65. http://ibm.biz/model-exchange Model Asset eXchange (MAX)
66. Tool #4: Data Asset eXchange Open Source Data Sets
67. http://ibm.biz/data-exchange Data Asset eXchange (DAX)
68. http://ibm.biz/codait-trusted-ai IBM CODAIT Trusted AI Work
69. 69 Agenda • Examples of Bias in Machine Learning. • Solutions to combat unwanted bias. • Tools to combat unwanted bias. • Resources and how to get involved.
70. https://www.ajlunited.org/fight
71. https://www.patreon.com/poetofcode
72. Photo by rawpixel on Unsplash No matter what it is our responsibility to build systems that are fair.
73. Thank you! Resources from this talk: https://bit.ly/WiTS-Bias Follow me: @Mo_Mack