Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility

• URL: http://arxiv.org/abs/2302.09183v1
• Date: Fri, 17 Feb 2023 23:23:45 GMT
• Title: Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility
• Authors: Mohammad Yaghini, Patty Liu, Franziska Boenisch, Nicolas Papernot
• Abstract summary: We argue that machine learning pipelines should not favor one objective over another. We propose impartially-specified models that show the inherent trade-offs between the objectives. We provide an answer to the question of where fairness mitigation should be integrated within a privacy-aware ML pipeline.
• Score: 28.946180502706504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between fairness, privacy, and utility are less well-understood. As a result, often only one objective is optimized, while the others are tuned as hyper-parameters. Because they implicitly prioritize certain objectives, such designs bias the model in pernicious, undetectable ways. To address this, we adopt impartiality as a principle: design of ML pipelines should not favor one objective over another. We propose impartially-specified models, which provide us with accurate Pareto frontiers that show the inherent trade-offs between the objectives. Extending two canonical ML frameworks for privacy-preserving learning, we provide two methods (FairDP-SGD and FairPATE) to train impartially-specified models and recover the Pareto frontier. Through theoretical privacy analysis and a comprehensive empirical study, we provide an answer to the question of where fairness mitigation should be integrated within a privacy-aware ML pipeline.

Related papers

• Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility [28.676852732262407]
  Federated Learning (FL) enables collaborative model training without data sharing.<n>We introduce a differentially private fair FL algorithm that transforms this multi-objective optimization into a zero-sum game.<n>Our theoretical analysis reveals a surprising inverse relationship, i.e., stricter privacy protection limits the system's ability to detect and correct demographic biases.
  arXiv  Detail & Related papers  (2025-10-30T07:14:55Z)
• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy [20.038766371144526]
  We introduce Differential privacy (DP) as the standard for privacy-preserving analysis, and introduce a fundamental trade-off between privacy guarantees and model performance.<n>In particular, we present the user with hypothetical trade-off curves and ask them to pick their preferred trade-off.<n>Our experiments on differentially private logistic regression and deep transfer learning across six real-world datasets show that our method converges to the optimal privacy-accuracy trade-off.
  arXiv  Detail & Related papers  (2025-09-04T15:02:10Z)
• The Statistical Fairness-Accuracy Frontier [50.323024516295725]
  Machine learning models must balance accuracy and fairness, but these goals often conflict.<n>A useful tool for understanding this trade-off is the fairness-accuracy frontier, which characterizes the set of models that cannot be simultaneously improved in both fairness and accuracy.<n>We study the FA frontier in the finite-sample regime, showing how it deviates from its population counterpart and quantifying the worst-case gap between them.
  arXiv  Detail & Related papers  (2025-08-25T03:01:35Z)
• Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models [91.24296813969003]
  This paper advocates integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML. We argue that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models.
  arXiv  Detail & Related papers  (2025-02-28T14:57:33Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Differentially Private Random Feature Model [52.468511541184895]
  We produce a differentially private random feature model for privacy-preserving kernel machines. We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness [6.881974834597426]
  Federated learning (FL) has emerged as a promising framework for distributed machine learning. We introduce CorBin-FL, a privacy mechanism that uses correlated binary quantization to achieve differential privacy. We also propose AugCorBin-FL, an extension that, in addition to PLDP, user-level and sample-level central differential privacy guarantees.
  arXiv  Detail & Related papers  (2024-09-20T00:23:44Z)
• Fairness-Aware Meta-Learning via Nash Bargaining [63.44846095241147]
  We introduce a two-stage meta-learning framework to address issues of group-level fairness in machine learning. The first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model. We show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.
  arXiv  Detail & Related papers  (2024-06-11T07:34:15Z)
• De-amplifying Bias from Differential Privacy in Language Model Fine-tuning [10.847913815093179]
  Fairness and privacy are two important values machine learning (ML) practitioners often seek to operationalize in models. We show that DP amplifies gender, racial, and religious bias when fine-tuning large language models. We demonstrate that Counterfactual Data Augmentation, a known method for addressing bias, also mitigates bias amplification by DP.
  arXiv  Detail & Related papers  (2024-02-07T00:30:58Z)
• Marginal Debiased Network for Fair Visual Recognition [59.05212866862219]
  We propose a novel marginal debiased network (MDN) to learn debiased representations. Our MDN can achieve a remarkable performance on under-represented samples.
  arXiv  Detail & Related papers  (2024-01-04T08:57:09Z)
• Automated discovery of trade-off between utility, privacy and fairness in machine learning models [8.328861861105889]
  We show how PFairDP can be used to replicate known results that were achieved through manual constraint setting process. We further demonstrate effectiveness of PFairDP with experiments on multiple models and datasets.
  arXiv  Detail & Related papers  (2023-11-27T10:28:44Z)
• Holistic Survey of Privacy and Fairness in Machine Learning [10.399352534861292]
  Privacy and fairness are crucial pillars of responsible Artificial Intelligence (AI) and trustworthy Machine Learning (ML) Despite significant interest, there remains an immediate demand for more in-depth research to unravel how these two objectives can be simultaneously integrated into ML models. We provide a thorough review of privacy and fairness in ML, including supervised, unsupervised, semi-supervised, and reinforcement learning.
  arXiv  Detail & Related papers  (2023-07-28T23:39:29Z)
• Universal Semi-supervised Model Adaptation via Collaborative Consistency Training [92.52892510093037]
  We introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA) We propose a collaborative consistency training framework that regularizes the prediction consistency between two models. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
  arXiv  Detail & Related papers  (2023-07-07T08:19:40Z)
• Theoretically Principled Federated Learning for Balancing Privacy and Utility [61.03993520243198]
  We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning.
  arXiv  Detail & Related papers  (2023-05-24T13:44:02Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Fair Bayesian Optimization [25.80374249896801]
  We introduce a general constrained Bayesian optimization framework to optimize the performance of any machine learning (ML) model. We apply BO with fairness constraints to a range of popular models, including random forests, boosting, and neural networks. We show that our approach is competitive with specialized techniques that enforce model-specific fairness constraints.
  arXiv  Detail & Related papers  (2020-06-09T08:31:08Z)

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.