FIGHT AI BIAS WITH… BIAS

I know, the title of this talk is like saying the only way to stop a bad Terminator is to use a good Terminator but hear me out. Human biases influence the outputs of an Al model. Al amplifies bias and socio- technical harms impact fairness, adoption, safety, and the well being, These harms disproportionately affect legally protected classes of individuals and groups in the United States.
It's so fitting that this year's theme for International Women's day was #BreakTheBias so join Noble as he returns to Strangeloop to expand on the topic of bias, deconstructs techniques to de-bias datasets by example for building intelligent systems that are fair and equitable while increasing trust and adoption.

Transcript

1. Fighting bias…with bias Noble Ackerson Dir. of Product (AI/ML) @ Ventera Corporation
3. Components of Responsible use of AI 3 HCML Fairness & Bias XAI Privacy & Data Risk Security
4. If AI is to be ambient, it better be fair Fairness in AI
5. Alexa not recognizing female voices or accents from a group of people Quantifying Fairness in AI Quality of service Opportunities withheld Job/loan screening systems excluding individuals or groups of individuals Traumatized data Trauma from collective psychological, emotional and cognitive distress experienced by an unprivileged class via IBM Research AI Fairness 360 aif360.mybluemix.net
6. We propagate our bias in the intelligent solutions we build twitter.com/nobleackerson medium.com/@nobleackerson
7. Photo by Noble Ackerson
8. Credit: Twitter | Starbucks
9. Credit: New York Times
10. Photo by Steve Helber | Credit: AP
11. Runaway Feedback Loops in Predictive Policing PredPol algorithms are already used by police departments in California, Florida, Maryland, and a few other States. Source: Conference on Fairness, Accountability, and Transparency
12. Bias in a Machine Learning context Adapted from: Cornell University ARXIV research 12 Algorithm 02 User Interaction 03 01 Data Behavioral Bias Presentation Bias Linking Bias Selection Bias Historical Bias Aggregation Bias Temporal Bias Social Bias Popularity Bias Ranking Bias Emergent Bias Resource: Catalog of Biases
13. Weʼre all impacted Data team, Researchers & Engineers Increase Data Understanding Create Better Algorithms Improve Performance Produce Robust Models Policy & Compliance Increase Trust Bias & Transparency Compliance and Regulation Reporting Consumers/End Users Calibrated Trust Bias & Transparency Understand Impact Reporting & Analyses Increase adoption 13
14. Policy & Compliance 14 ❏ Increase trust by being responsible ❏ Explaining bias for Compliance and regulation ❏ Reporting
15. Gaining regulatory trust increases innovation Demonstrating human-centered stewardship of user data, responsible use of production machine learning reduces overregulation.
16. Example: Amazon same-day delivery coverage Source: https://www.bloomberg.com/graphics/2016-amazon-same-day/ 16
17. 17 Roxbury, Boston Redlining
18. What is Explainable AI ? Input Feature 1. Classification 2. Prediction 3. Recommendation Black Box Input Feature Explained model 1. Classification 2. Prediction 3. Recommendation 1. Which features dominant? 2. How do features relate? 3. Why the model predicts this? DiffusionBee prompt “cyberpunk, synthwave, oracle explaining her prediction to an empty void”
19. You can’t debias that what you can’t explain Regulators are increasingly requiring model explanations when things go wrong with deployed learned models. 19 SHapley Additive exPlanations (SHAP)
20. Race Skin color Biometrics Religion Sexual Orientation Socioeconomic status Income Country of origin Questions to consider when looking for bias 1. Does your use-case or product specifically use protected classes? 2. Does your use-case use data correlated with protected classes? 3. Could your use-case negatively impact an individual's economic or other important life opportunities? 20
21. Policy and compliance ✓ Increase trust by being responsible ✓ Explaining for Compliance and regulation ✓ Reporting twitter.com/nobleackerson medium.com/@nobleackerson
22. ML team, Researchers & Engineers ❏ Increase data & model understanding ❏ Create better algorithms ❏ Produce robust models
23. Model behavior understanding is critical to fighting bias Debug and refine model behavior Pre-processing algorithms Deploy and Monitor Evaluate Build and Train Model Construct and Prepare Data Define Problem What-if Analysis TF 23 Explain Predictions Post-processing algorithms In-processing algorithms Github IBM AIF360 pre-process in-process post-process
24. Configure and Load dataset Set bias detection options, load dataset, and split between train and test
25. Test Fairness Metric Compute fairness metric on original training dataset
26. Fix what's wrong Mitigate bias by transforming the original dataset
27. Test Fairness Metric Compute fairness metric on transformed training dataset
28. vs Midjourney.ai prompt “A face-off between two fighters, one fighting on accuracy and the other fighting for fairness.” 28 Accurate Fair
29. Data Scientists, ML engineering, Research ✓ Increase data understanding ✓ Create better algorithms ✓ Produce robust, interpretable models twitter.com/nobleackerson medium.com/@nobleackerson
30. Consumers/End Users ❏ Increase adoption through calibrated trust ❏ Feedback: Context, Choice, and Control ❏ Designing for context to understand impact ❏ End-user Reporting & Analysis
31. Increase adoption through calibrated trust Not enough trust Too much trust Calibrated trust User wastes time searching for additional stores in an area Trust factor Trust factor Trust factor User doesn't double check before driving halfway across town User keeps away from a store confidently identified as busy 31
32. Recommendations when managing end-user feedback 1. Design in UX mechanisms to request feedback. 2. Build in functionality to respond to user feedback. 3. Interpret and use both implicit and explicit user feedback. DiffusionBee - Stable Diffusion prompt “depiction of the when things go very wrong with AI”
33. Consumers and End-Users ✓ Increase adoption through calibrated trust ✓ Feedback: Context, Choice, and Control ✓ Designing for context to understand impact ✓ End-user Reporting & Analysis twitter.com/nobleackerson medium.com/@nobleackerson
34. Debiasing techniques benefit non-protected classes Takeaways
35. Some packages lack adequate support Takeaways
36. Fighting bias…with bias is a balance of what was, what is, and what should be twitter.com/nobleackerson medium.com/@nobleackerson