paper-with-me

홈 › Papers

Flexibly Fair Representation Learning by Disentanglement

2019-06-06 · Elliot Creager, David Madras, Jörn-Henrik Jacobsen, Marissa A. Weis, Kevin Swersky, Toniann Pitassi, Richard Zemel

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also \emph{flexibly fair}, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

📄 PDF Abstract BibTeX arXiv:1906.02589

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementFairnessGeneral ClassificationRepresentation Learning

Similar Papers 제목 키워드 기반

On the Fairness of Disentangled Representations

2019-05-31 · NeurIPS 2019 12 · Francesco Locatello, Gabriele Abbati, Tom Rainforth, Stefan Bauer 외

Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this pap…

DisentanglementFairness

Investigating Speaker Embedding Disentanglement on Natural Read Speech

2023-08-08 · Michael Kuhlmann, Adrian Meise, Fritz Seebauer, Petra Wagner 외

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainabi…

DisentanglementFairnessRepresentation Learning

Learning Fair Representation via Distributional Contrastive Disentanglement

2022-06-17 · ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2022 8 · Changdae Oh, Heeji Won, Junhyuk So, Taero Kim 외

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, a…

Contrastive LearningDisentanglementDomain GeneralizationFairness+1

FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning

2022-08-22 · Siyi Du, Ben Hers, Nourhan Bayasi, Ghassan Hamarneh 외

Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types are usually underrepresented and have l…

AttributeContrastive LearningDeep LearningDisentanglement+3

Fair Representation Learning using Interpolation Enabled Disentanglement

2021-07-31 · Akshita Jha, Bhanukiran Vinzamuri, Chandan K. Reddy

With the growing interest in the machine learning community to solve real-world problems, it has become crucial to uncover the hidden reasoning behind their decisions by focusing on the fairness and auditing the predicti…

DisentanglementFairnessMutual Information EstimationRepresentation Learning