Model Selection's Disparate Impact in Real-World Deep Learning Applications

Jessica Zosa Forde, A. Feder Cooper, Kweku Kwegyir-Aggrey, Chris De Sa, Michael Littman

Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one source of such bias, human preferences in model selection, remains under-explored in terms of its role in disparate impact across demographic groups. Using a deep learning model trained on real-world medical imaging data, we verify our claim empirically and argue that choice of metric for model comparison can significantly bias model selection outcomes.

Knowledge Graph



Sign up or login to leave a comment