Abstract
We consider the problem of learning fair decision systems from data in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a counterfactual approach to disregard effects along unfair pathways that does not incur in the same loss of individual-specific information as previous approaches. Our method corrects observations adversely affected by the sensitive attribute, and uses these to form a decision. We leverage recent developments in deep learning and approximate inference to develop a VAE-type method that is widely applicable to complex nonlinear models.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
114 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Exploring latent discrimination through an Object-Relational Causal Inference method;Knowledge-Based Systems;2024-09
2. Causal Inference with Latent Variables: Recent Advances and Future Prospectives;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24
3. Your Neighbor Matters: Towards Fair Decisions Under Networked Interference;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24
4. Rethinking Fair Graph Neural Networks from Re-balancing;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24
5. Fairness: plurality, causality, and insurability;European Actuarial Journal;2024-06-19