Towards a Flexible Framework for Algorithmic Fairness

• URL: http://arxiv.org/abs/2010.07848v1
• Date: Thu, 15 Oct 2020 16:06:53 GMT
• Title: Towards a Flexible Framework for Algorithmic Fairness
• Authors: Philip Hacker, Emil Wiedemann, Meike Zehlike
• Abstract summary: In recent years, many different definitions for ensuring non-discrimination in algorithmic decision systems have been put forward. We present an algorithm that harnesses optimal transport to provide a flexible framework to interpolate between different fairness definitions.
• Score: 0.8379286663107844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Increasingly, scholars seek to integrate legal and technological insights to combat bias in AI systems. In recent years, many different definitions for ensuring non-discrimination in algorithmic decision systems have been put forward. In this paper, we first briefly describe the EU law framework covering cases of algorithmic discrimination. Second, we present an algorithm that harnesses optimal transport to provide a flexible framework to interpolate between different fairness definitions. Third, we show that important normative and legal challenges remain for the implementation of algorithmic fairness interventions in real-world scenarios. Overall, the paper seeks to contribute to the quest for flexible technical frameworks that can be adapted to varying legal and normative fairness constraints.

Related papers

• Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditing [0.0]
  The European Union's Artificial Intelligence Act takes effect on 1 August 2024. High-risk AI applications must adhere to stringent transparency and fairness standards. We propose a novel framework, which combines the strengths of counterfactual fairness and peer comparison strategy.
  arXiv  Detail & Related papers  (2024-08-05T15:35:34Z)
• Formalising Anti-Discrimination Law in Automated Decision Systems [1.560976479364936]
  We study the legal challenges in automated decision-making by analysing conventional algorithmic fairness approaches. By translating principles of anti-discrimination law into a decision-theoretic framework, we formalise discrimination. We propose a new, legally informed approach to developing systems for automated decision-making.
  arXiv  Detail & Related papers  (2024-06-29T10:59:21Z)
• A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning [54.20447310988282]
  We present a meta-algorithm alternating between regret minimization algorithms instanced at different (high and low) temporal abstractions. At the higher level, we treat the problem as a Semi-Markov Decision Process (SMDP), with fixed low-level policies, while at a lower level, inner option policies are learned with a fixed high-level policy.
  arXiv  Detail & Related papers  (2024-06-21T13:17:33Z)
• Fairness in AI: challenges in bridging the gap between algorithms and law [2.651076518493962]
  We identify best practices and strategies for the specification and adoption of fairness definitions and algorithms in real-world systems and use cases. We introduce a set of core criteria that need to be taken into account when selecting a specific fairness definition for real-world use case applications.
  arXiv  Detail & Related papers  (2024-04-30T08:59:00Z)
• Beyond Incompatibility: Trade-offs between Mutually Exclusive Fairness Criteria in Machine Learning and Law [2.959308758321417]
  We present a novel algorithm (FAir Interpolation Method: FAIM) for continuously interpolating between three fairness criteria. We demonstrate the effectiveness of our algorithm when applied to synthetic data, the COMPAS data set, and a new, real-world data set from the e-commerce sector.
  arXiv  Detail & Related papers  (2022-12-01T12:47:54Z)
• Reinforcement Learning with Stepwise Fairness Constraints [50.538878453547966]
  We introduce the study of reinforcement learning with stepwise fairness constraints. We provide learning algorithms with strong theoretical guarantees in regard to policy optimality and fairness violation.
  arXiv  Detail & Related papers  (2022-11-08T04:06:23Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Fairness and Explainability in Automatic Decision-Making Systems. A challenge for computer science and law [3.656085108168043]
  The paper offers a contribution to the interdisciplinary constructs of analyzing fairness issues in automatic algorithmic decisions. Section 1 shows that technical choices in supervised learning have social implications that need to be considered. Section 2 proposes a contextual approach to the issue of unintended group discrimination.
  arXiv  Detail & Related papers  (2022-05-14T01:08:47Z)
• Optimal Algorithms for Decentralized Stochastic Variational Inequalities [113.43047601775453]
  This work concentrates on the decentralized setting, which is increasingly important but not well understood. We present lower bounds for both communication and local iterations and construct optimal algorithms that match these lower bounds. Our algorithms are the best among the available not only in the decentralized case, but also in the deterministic and non-distributed literature.
  arXiv  Detail & Related papers  (2022-02-06T13:14:02Z)
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [61.317911756566126]
  We propose a Towards Fair Knowledge Transfer framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.
  arXiv  Detail & Related papers  (2020-10-23T06:29:09Z)
• Reinforcement Learning as Iterative and Amortised Inference [62.997667081978825]
  We use the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We show that taking this perspective allows us to identify parts of the algorithmic design space which have been relatively unexplored.
  arXiv  Detail & Related papers  (2020-06-13T16:10:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.