Let's talk about biases in machine learning! Ethics and Society Newsletter #2

Bias in ML is ubiquitous, and Bias in ML is complex; so complex in fact that no single technical intervention is likely to meaningfully address the problems it engenders. ML models, as sociotechnical systems, amplify social trends that may exacerbate inequities and harmful biases in ways that depend on their deployment context and are constantly evolving.

This means that developing ML systems with care requires vigilance and responding to feedback from those deployment contexts, which in turn we can facilitate by sharing lessons across contexts and developing tools to analyze signs of bias at every level of ML development.

This blog post from the Ethics and Society regulars @🤗 shares some of the lessons we have learned along with tools we have developed to support ourselves and others in our community’s efforts to better address bias in Machine Learning. The first part is a broader reflection on bias and its context. If you’ve already read it and are coming back specifically for the tools, feel free to jump to the datasets or models section!

Selection of tools developed by 🤗 team members to address bias in ML

Table of contents:

• On Machine Biases
  • Machine Bias: from ML Systems to Risks
  • Putting Bias in Context
• Tools and Recommendations
  • Addressing Bias throughout ML Development
    • Task Definition
    • Dataset Curation
    • Model Training
  • Overview of 🤗 Bias Tools

Machine Bias: from ML Systems to Personal and Social Risks

ML systems allow us to automate complex tasks at a scale never seen before as they are deployed in more sectors and use cases. When the technology works at its best, it can help smooth interactions between people and technical systems, remove the need for highly repetitive work, or unlock new ways of processing information to support research.

Putting Bias in Context

Excerpt on considerations of ML uses context and people from the Model Card Guidebook

Addressing Bias throughout the ML Development Cycle

Ready for some practical advice yet? Here we go 🤗