Name
Abstract | ||
|---|---|---|
Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept of fairness requires causal reasoning. We then review existing works and identify future opportunities for applying data management techniques to causal algorithmic fairness. |
Year | Venue | Field |
|---|---|---|
2019 | IEEE Data Eng. Bull. | Data science,Data mining,Computer science,Data management |
DocType | Volume | Issue |
Journal | 42 | 3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Babak Salimi | 1 | 25 | 8.62 |
| Bill Howe | 2 | 1520 | 94.44 |
| Dan Suciu | 3 | 9625 | 1349.54 |