Timezone: »

Post-processing for Individual Fairness
Felix Petersen · Debarghya Mukherjee · Yuekai Sun · Mikhail Yurochkin

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

Post-processing in algorithmic fairness is a versatile approach for correcting bias in ML systems that are already used in production. The main appeal of post-processing is that it avoids expensive retraining. In this work, we propose general post-processing algorithms for individual fairness (IF). We consider a setting where the learner only has access to the predictions of the original model and a similarity graph between individuals, guiding the desired fairness constraints. We cast the IF post-processing problem as a graph smoothing problem corresponding to graph Laplacian regularization that preserves the desired "treat similar individuals similarly" interpretation. Our theoretical results demonstrate the connection of the new objective function to a local relaxation of the original individual fairness. Empirically, our post-processing algorithms correct individual biases in large-scale NLP models such as BERT, while preserving accuracy.

Author Information

Felix Petersen (University of Konstanz)
Debarghya Mukherjee (University of Michigan)
Yuekai Sun (University of Michigan)
Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab)

More from the Same Authors