{
  "id": "2308.01923",
  "version": "v1",
  "published": "2023-07-25T14:01:23.000Z",
  "updated": "2023-07-25T14:01:23.000Z",
  "title": "An Empirical Study on Fairness Improvement with Multiple Protected Attributes",
  "authors": [
    "Zhenpeng Chen",
    "Jie M. Zhang",
    "Federica Sarro",
    "Mark Harman"
  ],
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CY",
    "cs.SE"
  ],
  "abstract": "Existing research mostly improves the fairness of Machine Learning (ML) software regarding a single protected attribute at a time, but this is unrealistic given that many users have multiple protected attributes. This paper conducts an extensive study of fairness improvement regarding multiple protected attributes, covering 11 state-of-the-art fairness improvement methods. We analyze the effectiveness of these methods with different datasets, metrics, and ML models when considering multiple protected attributes. The results reveal that improving fairness for a single protected attribute can largely decrease fairness regarding unconsidered protected attributes. This decrease is observed in up to 88.3% of scenarios (57.5% on average). More surprisingly, we find little difference in accuracy loss when considering single and multiple protected attributes, indicating that accuracy can be maintained in the multiple-attribute paradigm. However, the effect on precision and recall when handling multiple protected attributes is about 5 times and 8 times that of a single attribute. This has important implications for future fairness research: reporting only accuracy as the ML performance metric, which is currently common in the literature, is inadequate.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-07-25T14:01:23.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "empirical study",
      "regarding multiple protected attributes",
      "single protected attribute",
      "regarding unconsidered protected attributes",
      "state-of-the-art fairness improvement methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}