The aim of this tutorial is to point out the limitations existing in current association-based approaches, introduce a causal modeling-based framework for anti-discrimination learning, and suggest potential future research directions.
Anti-discrimination learning is an increasingly important task in data mining and machine learning fields. Discrimination discovery is the problem of unveiling discriminatory practices by analyzing a dataset of historical decision records, and discrimination prevention aims to remove discrimination by modifying the biased data and/or the predictive algorithms. Discrimination is causal, which means that to prove discrimination one needs to derive a causal relationship rather than an association relationship. Although it is well-known that association does not mean causation, the gap between association and causation is not given enough attention by many researchers.
The tutorial is organized into six parts, including an introduction part, a literature review part, three main technical parts, and a concluding part.