Situation Testing-Based Discrimination Discovery: A Causal Inference Approach
By Lu Zhang, Yongkai Wu, Xintao Wu. 2016
60 citations recorded by the source corpus.
Subfields: Causal Inference & Discovery, AI Ethics, Fairness & Society
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Causal Inference & Discovery
- Xintao Wu
- Lu Zhang
- Yongkai Wu
- Silvia Chiappa
- Indrė Žliobaitė
- Asim Karim
- Faisal Kamiran
- Salvatore Ruggieri
In AI Ethics, Fairness & Society
- Xintao Wu
- Lu Zhang
- Yongkai Wu
- Indrė Žliobaitė
- Silvia Chiappa
- Faisal Kamiran
- Asim Karim
- Salvatore Ruggieri
Citations in the corpus
- Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, methodology): “Studies in [7], [8], [9] are built on causal modeling and the associated causal graph, but cannot deal with indirect discrimination.”
- A Causal Framework for Discovering and Removing Direct and Indirect Discrimination (2016, background): “(Luong, Ruggieri, and Turini 2011; Zhang, Wu, and Wu 2016b) dealt with the individual discrimination by finding a group of similar individuals.”
- PC-Fairness: A Unified Framework for Measuring Causality-based Fairness (2019, unknown): “Table 1: Connection between previous fairness notions and PC fairness Description References Relating to PC fairness Total effect [19, 16] O = ∅ and π = Π (System) Direct discrimination [19, 7, 16] O = ∅ or {S} and π = πd = {S → Ŷ } (System) Indirect discrimination [19, 7, 16] O = ∅ or {S} and π = π”
- Measuring discrimination in algorithmic decision making (2017, background): “The second condition ensures that there is no indirect discrimination, which occurs when apparently neutral provision, criteria or practice would put persons of a protected ground at a particular disadvantage compared with other persons.”
- Causal Discrimination Discovery Through Propensity Score Analysis (2016, background): “oritism. The construction of the causal network is however impractical for a large number of attributevalue pairs, and it also requires human intervention in providing a temporal order between pairs. [36] extends, as we do, the situation testing approach of [26] to causal reasoning. They adopt a Cau”
- Anti-discrimination learning: a causal modeling-based framework (2017, methodology): “It turns out that the above requirement is a natural result when the causal graph is used as a guideline of measuring the similarity, as shown in [40].”