Litcius/Paper detail

Measuring Model Biases in the Absence of Ground Truth

Osman Aka, Ken Burke, Alex Bauerle, Christina Greer, Margaret Mitchell

202116 citationsDOIOpen Access PDF

Abstract

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a model may have learned, for example between labels and identity subgroups. Further, measuring a model's bias requires a fully annotated evaluation dataset which may not be easily available in practice.

Topics & Concepts

Measure (data warehouse)Identity (music)Artificial intelligenceComputer scienceGround truthMachine learningVariation (astronomy)Identification (biology)Natural language processingTerm (time)Observational errorData collectionPsychologySet (abstract data type)Training setContrast (vision)Machine Learning and Data ClassificationExplainable Artificial Intelligence (XAI)Domain Adaptation and Few-Shot Learning
Measuring Model Biases in the Absence of Ground Truth | Litcius