Bias in Machine Learning -- What is it Good for?

Abstract

In public media as well as in scientific publications, the term \emph{bias} is used in conjunction with machine learning in many different contexts, and with many different meanings. This paper proposes a taxonomy of these different meanings, terminology, and definitions by surveying the, primarily scientific, literature on machine learning. In some cases, we suggest extensions and modifications to promote a clear terminology and completeness. The survey is followed by an analysis and discussion on how different types of biases are connected and depend on each other. We conclude that there is a complex relation between bias occurring in the machine learning pipeline that leads to a model, and the eventual bias of the model (which is typically related to social discrimination). The former bias may or may not influence the latter, in a sometimes bad, and sometime good way.

References in corpus (8)

• Efficient Estimation of Word Representations in Vector Space
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Causal Reasoning for Algorithmic Fairness
• Bias In, Bias Out? Evaluating the Folk Wisdom
• Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems

Cited by in corpus (2)

• Why we need biased AI -- How including cognitive and ethical machine biases can enhance AI systems
• Shedding light on underrepresentation and Sampling Bias in machine learning