Probably Approximate Shapley Fairness with Applications in Machine Learning

• URL: http://arxiv.org/abs/2212.00630v1
• Date: Thu, 1 Dec 2022 16:28:20 GMT
• Title: Probably Approximate Shapley Fairness with Applications in Machine Learning
• Authors: Zijian Zhou, Xinyi Xu, Rachael Hwee Ling Sim, Chuan Sheng Foo, Kian Hsiang Low
• Abstract summary: The Shapley value (SV) is adopted in various scenarios in machine learning (ML) As exact SVs are infeasible to compute in practice, SV estimates are approximated instead. This approximation step raises an important question: do the SV estimates preserve the fairness guarantees of exact SVs? We observe that the fairness guarantees of exact SVs are too restrictive for SV estimates.
• Score: 18.05783128571293
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The Shapley value (SV) is adopted in various scenarios in machine learning (ML), including data valuation, agent valuation, and feature attribution, as it satisfies their fairness requirements. However, as exact SVs are infeasible to compute in practice, SV estimates are approximated instead. This approximation step raises an important question: do the SV estimates preserve the fairness guarantees of exact SVs? We observe that the fairness guarantees of exact SVs are too restrictive for SV estimates. Thus, we generalise Shapley fairness to probably approximate Shapley fairness and propose fidelity score, a metric to measure the variation of SV estimates, that determines how probable the fairness guarantees hold. Our last theoretical contribution is a novel greedy active estimation (GAE) algorithm that will maximise the lowest fidelity score and achieve a better fairness guarantee than the de facto Monte-Carlo estimation. We empirically verify GAE outperforms several existing methods in guaranteeing fairness while remaining competitive in estimation accuracy in various ML scenarios using real-world datasets.

Related papers

• Post-hoc Probabilistic Vision-Language Models [51.12284891724463]
  Vision-language models (VLMs) have found remarkable success in classification, retrieval, and generative tasks. We propose post-hoc uncertainty estimation in VLMs that does not require additional training. Our results show promise for safety-critical applications of large-scale models.
  arXiv  Detail & Related papers  (2024-12-08T18:16:13Z)
• Probabilistic Conformal Prediction with Approximate Conditional Validity [81.30551968980143]
  We develop a new method for generating prediction sets that combines the flexibility of conformal methods with an estimate of the conditional distribution. Our method consistently outperforms existing approaches in terms of conditional coverage.
  arXiv  Detail & Related papers  (2024-07-01T20:44:48Z)
• Equal Opportunity of Coverage in Fair Regression [50.76908018786335]
  We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. We propose Equal Opportunity of Coverage (EOC) that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level.
  arXiv  Detail & Related papers  (2023-11-03T21:19:59Z)
• A Note on "Towards Efficient Data Valuation Based on the Shapley Value'' [7.4011772612133475]
  The Shapley value (SV) has emerged as a promising method for data valuation. Group Testing-based SV estimator achieves favorable sample complexity.
  arXiv  Detail & Related papers  (2023-02-22T15:13:45Z)
• Secure Shapley Value for Cross-Silo Federated Learning (Technical Report) [14.539140693803601]
  Shapley value (SV) is a fair and principled metric for contribution evaluation in cross-silo federated learning (cross-silo FL) Existing SV calculation methods for FL assume that the server can access the raw FL models and public test data. We propose SecSV, an efficient two-server protocol with the following novel features.
  arXiv  Detail & Related papers  (2022-09-11T13:10:29Z)
• Fair and efficient contribution valuation for vertical federated learning [49.50442779626123]
  Federated learning is a popular technology for training machine learning models on distributed data sources without sharing data. The Shapley value (SV) is a provably fair contribution valuation metric originated from cooperative game theory. We propose a contribution valuation metric called vertical federated Shapley value (VerFedSV) based on SV.
  arXiv  Detail & Related papers  (2022-01-07T19:57:15Z)
• Large-Scale Methods for Distributionally Robust Optimization [53.98643772533416]
  We prove that our algorithms require a number of evaluations gradient independent of training set size and number of parameters. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9--36 times more efficient than full-batch methods.
  arXiv  Detail & Related papers  (2020-10-12T17:41:44Z)
• A Principled Approach to Data Valuation for Federated Learning [73.19984041333599]
  Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. The Shapley value (SV) defines a unique payoff scheme that satisfies many desiderata for a data value notion. This paper proposes a variant of the SV amenable to FL, which we call the federated Shapley value.
  arXiv  Detail & Related papers  (2020-09-14T04:37:54Z)
• Robust Validation: Confident Predictions Even When Distributions Shift [19.327409270934474]
  We describe procedures for robust predictive inference, where a model provides uncertainty estimates on its predictions rather than point predictions. We present a method that produces prediction sets (almost exactly) giving the right coverage level for any test distribution in an $f$-divergence ball around the training population. An essential component of our methodology is to estimate the amount of expected future data shift and build robustness to it.
  arXiv  Detail & Related papers  (2020-08-10T17:09:16Z)

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.