paper-with-me

홈 › Papers

A Variational Approach to Privacy and Fairness

2020-06-11 · Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund

In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy and fairness optimization problems that we propose. In this formulation, we aim to generate representations of the data that keep a prescribed level of the relevant information that is not shared by the private or sensitive data, while minimizing the remaining information they keep. The proposed approach (i) exhibits the similarities of the privacy and fairness problems, (ii) allows us to control the trade-off between utility and privacy or fairness through the Lagrange multiplier parameter, and (iii) can be comfortably incorporated to common representation learning algorithms such as the VAE, the $\beta$-VAE, the VIB, or the nonlinear IB.

📄 PDF Abstract BibTeX arXiv:2006.06332

Code (2)

burklight/VariationalPrivacyFairness 공식 구현 pytorch
BehroozRazeghi/Variational-Leakage tf

Tasks

FairnessRepresentation Learning

Methods 이 논문이 사용한 방법론

USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacy

2024-02-16 · Songjie Xie, Youlong Wu, Jiaxuan Li, Ming Ding 외

As machine learning (ML) becomes more prevalent in human-centric applications, there is a growing emphasis on algorithmic fairness and privacy protection. While previous research has explored these areas as separate obje…

FairnessRepresentation Learning

Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation

2025-08-29 · Tobias Hyrup, Emmanouil Panagiotou, Arjun Roy, Arthur Zimek 외 arxiv

As privacy regulations such as the GDPR and HIPAA and responsibility frameworks for artificial intelligence such as the AI Act gain traction, the ethical and responsible use of real-world data faces increasing constraint…

Synthetic Data Generation

Fairness without the sensitive attribute via Causal Variational Autoencoder

2021-09-10 · Vincent Grari, Sylvain Lamprier, Marcin Detyniecki

In recent years, most fairness strategies in machine learning models focus on mitigating unwanted biases by assuming that the sensitive information is observed. However this is not always possible in practice. Due to pri…

AttributeFairness

Fairness Risks for Group-conditionally Missing Demographics

2024-02-20 · Kaiqi Jiang, Wenzhe Fan, Mao Li, Xinhua Zhang

Fairness-aware classification models have gained increasing attention in recent years as concerns grow on discrimination against some demographic groups. Most existing models require full knowledge of the sensitive featu…

Fairness

Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning

2023-11-30 · Kangkang Sun, Xiaojin Zhang, Xi Lin, Gaolei Li 외

Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm that guarantees user privacy and prevents the risk of data leakage due to the advantage of the client's local training. Research…

FairnessFederated Learning