ML Model Fairness Research from IBM, Google & Others


In this post, you would learn about details (brief information and related URLs) on some of the research work done on AI/machine learning model ethics & fairness (bias) in companies such as Google, IBM, Microsoft, and others. This post will be updated from time-to-time covering latest projects/research work happening in various companies. You may want to bookmark the page for checking out the latest details.

Before we go ahead, it may be worth visualizing a great deal of research happening in the field of machine learning model fairness represented using the cartoon below, which is taken from the course CS 294: Fairness in Machine Learning course taught at UC Berkley.

Machine learning model fairness research

IBM Research for ML Model Fairness

Google Research/Courses on ML Model Fairness

Here are some links in relation to machine learning model fairness.

  • Machine learning fairness
  • Google Machine Learning crash course – Fairness module: In addition, the module also presents information on some of the following:
    • Types of Bias. Discussed are some of the following different types of bias:
      • Selection bias (coverage bias, non-response bias, sampling bias)
      • Group attribution bias (in-group bias, out-group homogeneity bias)
      • Implicit bias (confirmation & experimenter’s bias)
    • Identifying bias: The following are some of the topics discussed for identifying the bias:
      • Missing feature values
      • Unexpected feature values
      • Data Skew
    • Evaluating Bias: Confusion matrix (accuracy vs recall or sensitivity) could be used to evaluate bias for different groups.
  • Interactive visualization on attacking discrimination with smarter machine learning

Microsoft Research on Model FATE


In this post, you learned about details on courses and research initiatives happening in the area of machine learning model fairness in different companies such as Google, IBM, and others.

Ajitesh Kumar
Follow me

Leave A Reply

Time limit is exhausted. Please reload the CAPTCHA.