Latent Space Smoothing for Individually Fair Representations
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair representations, i.e., guaranteeing that similar individuals are treated similarly, remains challenging in high-dimensional settings such as computer vision. In this work, we introduce LASSI, the first representation learning method for certifying individual fairness of high-dimensional data. Our key insight is to leverage recent advances in generative modeling to capture the set of similar individuals in the generative latent space. This enables us to learn individually fair representations that map similar individuals close together by using adversarial training to minimize the distance between their representations. Finally, we employ randomized smoothing to provably map similar individuals close together, in turn ensuring that local robustness verification of the downstream application results in end-to-end fairness certification. Our experimental evaluation on challenging real-world image data demonstrates that our method increases certified individual fairness by up to 90% without significantly affecting task utility.
Code (1)
Tasks
FairnessRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Certified Individually Fair Representations
Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness constraints, each requiring similar treatmen…
FairnessRepresentation LearningLearning Smooth and Fair Representations
Organizations that own data face increasing legal liability for its discriminatory use against protected demographic groups, extending to contractual transactions involving third parties access and use of the data. This …
FairnessRepresentation LearningIndividual Fairness Revisited: Transferring Techniques from Adversarial Robustness
We turn the definition of individual fairness on its head---rather than ascertaining the fairness of a model given a predetermined metric, we find a metric for a given model that satisfies individual fairness. This can f…
Adversarial RobustnessFairnessAdversarial Stacked Auto-Encoders for Fair Representation Learning
Training machine learning models with the only accuracy as a final goal may promote prejudices and discriminatory behaviors embedded in the data. One solution is to learn latent representations that fulfill specific fair…
FairnessRepresentation LearningWhen predict can also explain: few-shot prediction to select better neural latents
Latent variable models serve as powerful tools to infer underlying dynamics from observed neural activity. However, due to the absence of ground truth data, prediction benchmarks are often employed as proxies. In this st…
Prediction