LiFT: A Scalable Framework for Measuring Fairness in ML Applications

Abstract

Many internet applications are powered by machine learned models, which are usually trained on labeled datasets obtained through either implicit / explicit user feedback signals or human judgments. Since societal biases may be present in the generation of such datasets, it is possible for the trained models to be biased, thereby resulting in potential discrimination and harms for disadvantaged groups. Motivated by the need for understanding and addressing algorithmic bias in web-scale ML systems and the limitations of existing fairness toolkits, we present the LinkedIn Fairness Toolkit (LiFT), a framework for scalable computation of fairness metrics as part of large ML systems. We highlight the key requirements in deployed settings, and present the design of our fairness measurement system. We discuss the challenges encountered in incorporating fairness tools in practice and the lessons learned during deployment at LinkedIn. Finally, we provide open problems based on practical experience.

arXiv commentAccepted for publication in CIKM 2020

References in corpus (13)

• Scikit-learn: Machine Learning in Python
• TensorFlow: A system for large-scale machine learning
• Model Cards for Model Reporting
• Equality of Opportunity in Supervised Learning
• Improving fairness in machine learning systems: What do industry practitioners need?
• Fairness Testing: Testing Software for Discrimination
• Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search
• Fairness in Machine Learning
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
• Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction
• Aequitas: A Bias and Fairness Audit Toolkit
• Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements

Cited by in corpus (14)

• Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey
• Behavioral Use Licensing for Responsible AI
• Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey
• Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
• A Scoping Study of Evaluation Practices for Responsible AI Tools: Steps Towards Effectiveness Evaluations
• De-biasing "bias" measurement
• "What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness
• The "Who", "What", and "How" of Responsible AI Governance: A Systematic Review and Meta-Analysis of (Actor, Stage)-Specific Tools
• Subverting Fair Image Search with Generative Adversarial Perturbations
• Disentangling and Operationalizing AI Fairness at LinkedIn
• LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
• Nishpaksh: TEC Standard-Compliant Framework for Fairness Auditing and Certification of AI Models
• Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study
• Towards Integrating Fairness Transparently in Industrial Applications