A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition

• URL: http://arxiv.org/abs/2406.04562v2
• Date: Wed, 23 Oct 2024 22:25:02 GMT
• Title: A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
• Authors: Faisal Hamman, Sanghamitra Dutta,
• Abstract summary: This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID) In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs.
• Score: 6.702661996542768
• License:
• Abstract: This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.

Related papers

• A Semiparametric Approach to Causal Inference [2.092897805817524]
  In causal inference, an important problem is to quantify the effects of interventions or treatments. In this paper, we employ a semiparametric density ratio model (DRM) to characterize the counterfactual distributions. Our model offers flexibility by avoiding strict parametric assumptions on the counterfactual distributions.
  arXiv  Detail & Related papers  (2024-11-01T18:03:38Z)
• Goodhart's Law Applies to NLP's Explanation Benchmarks [57.26445915212884]
  We critically examine two sets of metrics: the ERASER metrics (comprehensiveness and sufficiency) and the EVAL-X metrics. We show that we can inflate a model's comprehensiveness and sufficiency scores dramatically without altering its predictions or explanations on in-distribution test inputs. Our results raise doubts about the ability of current metrics to guide explainability research, underscoring the need for a broader reassessment of what precisely these metrics are intended to capture.
  arXiv  Detail & Related papers  (2023-08-28T03:03:03Z)
• Reconciling Predictive and Statistical Parity: A Causal Approach [68.59381759875734]
  We propose a new causal decomposition formula for the fairness measures associated with predictive parity. We show that the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions.
  arXiv  Detail & Related papers  (2023-06-08T09:23:22Z)
• Fairness and robustness in anti-causal prediction [73.693135253335]
  Robustness to distribution shift and fairness have independently emerged as two important desiderata required of machine learning models. While these two desiderata seem related, the connection between them is often unclear in practice. By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness.
  arXiv  Detail & Related papers  (2022-09-20T02:41:17Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Bounding and Approximating Intersectional Fairness through Marginal Fairness [7.954748673441148]
  Discrimination in machine learning often arises along multiple dimensions. It is desirable to ensure emphintersectional fairness -- i.e., that no subgroup is discriminated against.
  arXiv  Detail & Related papers  (2022-06-12T19:53:34Z)
• Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
  We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
  arXiv  Detail & Related papers  (2022-05-20T15:02:53Z)
• Skeptical binary inferences in multi-label problems with sets of probabilities [0.0]
  We consider the problem of making distributionally robust, skeptical inferences for the multi-label problem. By skeptical we understand that we consider as valid only those inferences that are true for every distribution within this set. We study in particular the Hamming loss case, a common loss function in multi-label problems, showing how skeptical inferences can be made in this setting.
  arXiv  Detail & Related papers  (2022-05-02T05:37:53Z)
• Gradual (In)Compatibility of Fairness Criteria [0.0]
  Impossibility results show that important fairness measures cannot be satisfied at the same time under reasonable assumptions. This paper explores whether we can satisfy and/or improve these fairness measures simultaneously to a certain degree.
  arXiv  Detail & Related papers  (2021-09-09T16:37:30Z)
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation [61.61555159755858]
  We propose a method called NaLP to conduct link prediction on n-ary relational data. We represent each n-ary relational fact as a set of its role and role-value pairs. Experimental results validate the effectiveness and merits of the proposed methods.
  arXiv  Detail & Related papers  (2021-04-21T09:06:54Z)

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.