Individual Fairness in Hindsight

2018-12-10 · Swati Gupta, Vijay Kamble

Since many critical decisions impacting human lives are increasingly being made by algorithms, it is important to ensure that the treatment of individuals under such algorithms is demonstrably fair under reasonable notions of fairness. One compelling notion proposed in the literature is that of individual fairness (IF), which advocates that similar individuals should be treated similarly (Dwork et al. 2012). Originally proposed for offline decisions, this notion does not, however, account for temporal considerations relevant for online decision-making. In this paper, we extend the notion of IF to account for the time at which a decision is made, in settings where there exists a notion of conduciveness of decisions as perceived by the affected individuals. We introduce two definitions: (i) fairness-across-time (FT) and (ii) fairness-in-hindsight (FH). FT is the simplest temporal extension of IF where treatment of individuals is required to be individually fair relative to the past as well as future, while in FH, we require a one-sided notion of individual fairness that is defined relative to only the past decisions. We show that these two definitions can have drastically different implications in the setting where the principal needs to learn the utility model. Linear regret relative to optimal individually fair decisions is inevitable under FT for non-trivial examples. On the other hand, we design a new algorithm: Cautious Fair Exploration (CaFE), which satisfies FH and achieves sub-linear regret guarantees for a broad range of settings. We characterize lower bounds showing that these guarantees are order-optimal in the worst case. FH can thus be embedded as a primary safeguard against unfair discrimination in algorithmic deployments, without hindering the ability to take good decisions in the long-run.

📄 PDF Abstract BibTeX arXiv:1812.04069

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making Fairness

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

2021-02-13 · Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright 외

Hindsight rationality is an approach to playing general-sum games that prescribes no-regret learning dynamics for individual agents with respect to a set of deviations, and further describes jointly rational behavior amo…

counterfactual Decision Making Form Sequential Decision Making

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections

2022-05-24 · Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright 외

counterfactual Decision Making Form Sequential Decision Making

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

2023-07-21 · Akash Velu, Skanda Vaidyanath, Dilip Arumugam

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are …

Decision Making Deep Reinforcement Learning Off-policy evaluation Policy Gradient Methods+3

Bridging the Fairness Divide: Achieving Group and Individual Fairness in Graph Neural Networks

2024-04-26 · Duna Zhan, Dongliang Guo, Pengsheng Ji, Sheng Li

Graph neural networks (GNNs) have emerged as a powerful tool for analyzing and learning from complex data structured as graphs, demonstrating remarkable effectiveness in various applications, such as social network analy…

Drug Discovery Fairness Graph Learning Graph Neural Network+1

Individual Fairness In Strategic Classification

2026-02-04 · Zhiqun Zuo, Mohammad Mahdi Khalili arxiv

Strategic classification, where individuals modify their features to influence machine learning (ML) decisions, presents critical fairness challenges. While group fairness in this setting has been widely studied, individ…