Anti-discrimination learning: a causal modeling-based framework

By Lu Zhang, Xintao Wu. 2017

54 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety Research, Sociology and Political Science, 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 Artificial Intelligence

1. Silvia Chiappa
2. Xintao Wu
3. Lu Zhang
4. Bernhard Schölkopf
5. Yongkai Wu
6. Adrian Weller
7. Krishna P. Gummadi
8. Dominik Janzing

In Safety Research

1. Silvia Chiappa
2. Lu Zhang
3. Xintao Wu
4. Yongkai Wu
5. Adrian Weller
6. Luca Oneto
7. Bernhard Schölkopf
8. Krishna P. Gummadi

In Sociology and Political Science

1. Lu Zhang
2. Silvia Chiappa
3. Xintao Wu
4. Yongkai Wu
5. Adrian Weller
6. Bernhard Schölkopf
7. Krishna P. Gummadi
8. Pedro A. Ortega

In Causal Inference & Discovery

1. Silvia Chiappa
2. Bernhard Schölkopf
3. Xintao Wu
4. Lu Zhang
5. Dominik Janzing
6. Yongkai Wu
7. Jan Peters
8. Adrian Weller

In AI Ethics, Fairness & Society

1. Silvia Chiappa
2. Xintao Wu
3. Lu Zhang
4. Yongkai Wu
5. Krishna P. Gummadi
6. Adrian Weller
7. Faisal Kamiran
8. Luca Oneto

Citations in the corpus

• Path-Specific Counterfactual Fairness (2018, methodology): “…argued (Qureshi et al., 2016; Bonchi et al., 2017; Kilbertus et al., 2017; Kusner et al., 2017; Nabi & Sh-pitser, 2018; Russell et al., 2017; Zhang et al., 2017; Zhang & Wu, 2017; Zhang & Bareinboim, 2018) that using a causal framework (Pearl, 2000; Dawid, 2007; Pearl et al., 2016; Peters…”
• Avoiding Discrimination through Causal Reasoning (2017, methodology): “Causal graphical conditions to identify meaningful partitions have been proposed for the discovery and prevention of certain types of discrimination by preprocessing the data [18].”
• Achieving Non-Discrimination in Data Release (2016, background): “Studies in [36–39] are built on the causal graph and causal modeling, and [35] provides a review of these works.”
• Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings (2019, methodology): “omen? A nuanced account of the situation can be obtained using causal graphs (Bonchi et al., 2017; Chiappa, 2019; Kilbertus et al., 2017; Kusner et al., 2017; Mancuhan and Clifton, 2014; Pearl, 2009; Zhang and Wu, 2017). Using a causal graph similar to the one represented in Figure 5a, Pearl (2009) ”
• Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction (2018, background): “Inspired by arguments for applying causal reasoning in fairness [8, 34, 39, 42, 51, 54, 63], fairness judgments might be influenced by whether a feature is likely to cause (i.”
• Causal Discrimination Discovery Through Propensity Score Analysis (2016, background): “ting of tuples to uniform the distribution in the protected and unprotected groups, without requiring hu4 B. Qureshi et al. man intervention. On the other hand, graphical and structural causal models [34,35], are able to distinguish and to explain the effects of direct, indirect, and spurious discri”