Post-processing for Individual Fairness

Felix Petersen, Debarghya Mukherjee, Yuekai Sun, Mikhail Yurochkin

Keywords: algorithmic fairness, graph Laplacian, post-processing, fairness, individual fairness

TL;DR: Post-processing algorithms for achieving individual fairness.

Abstract: 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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/Felix-Petersen/fairness-post-processing

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2110.13796/code)