Intervening on early readouts for mitigating spurious features and simplicity bias

Posted by Rishabh Tiwari, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research

Machine learning models in the real world are often trained on limited data that may contain unintended statistical biases. For example, in the CELEBA celebrity image dataset, a disproportionate number of female celebrities have blond hair, leading to classifiers incorrectly predicting “blond” as the hair color for most female faces — here, gender is a spurious feature for predicting hair color. Such unfair biases could have …

bias biases celebrities celebrity data dataset deep learning example features google google research hair icml image machine machine learning machine learning models ml fairness research researcher research scientist simplicity statistical supervised learning world