paper-with-me

Papers

Fairness Through Computationally-Bounded Awareness

2018-03-08 · NeurIPS 2018 12 · Michael P. Kim, Omer Reingold, Guy N. Rothblum

We study the problem of fair classification within the versatile framework of Dwork et al. [ITCS '12], which assumes the existence of a metric that measures similarity between pairs of individuals. Unlike earlier work, we do not assume that the entire metric is known to the learning algorithm; instead, the learner can query this arbitrary metric a bounded number of times. We propose a new notion of fairness called metric multifairness and show how to achieve this notion in our setting. Metric multifairness is parameterized by a similarity metric $d$ on pairs of individuals to classify and a rich collection ${\cal C}$ of (possibly overlapping) "comparison sets" over pairs of individuals. At a high level, metric multifairness guarantees that similar subpopulations are treated similarly, as long as these subpopulations are identified within the class ${\cal C}$.

📄 PDF Abstract BibTeX arXiv:1803.03239

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models

2024-10-22 · Chen Qian, Dongrui Liu, Jie Zhang, Yong liu 외

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fin…

Fairness

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data

2022-07-21 · Wenda Chu, Chulin Xie, Boxin Wang, Linyi Li 외

Federated learning (FL) allows agents to jointly train a global model without sharing their local data. However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the…

FairnessFederated Learning

Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs

2025-02-04 · Angelina Wang, Michelle Phan, Daniel E. Ho, Sanmi Koyejo

Algorithmic fairness has conventionally adopted the mathematically convenient perspective of racial color-blindness (i.e., difference unaware treatment). However, we contend that in a range of important settings, group d…

16kDescriptiveFairness

Active Fairness Instead of Unawareness

2020-09-14 · Boris Ruf, Marcin Detyniecki

The possible risk that AI systems could promote discrimination by reproducing and enforcing unwanted bias in data has been broadly discussed in research and society. Many current legal standards demand to remove sensitiv…

Fairness

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

2024-10-10 · Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu 외

Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). How…

FairnessRAGRetrievalRetrieval-augmented Generation