Individual Fairness Guarantees for Neural Networks

• URL: http://arxiv.org/abs/2205.05763v1
• Date: Wed, 11 May 2022 20:21:07 GMT
• Title: Individual Fairness Guarantees for Neural Networks
• Authors: Elias Benussi (1), Andrea Patane (1), Matthew Wicker (1), Luca Laurenti (2) and Marta Kwiatkowska (1) ((1) University of Oxford, (2) TU Delft)
• Abstract summary: We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs) We work with the $epsilon$-$delta$-IF formulation, which requires that the output difference between any pair of $epsilon$-similar individuals is bounded by a maximum decision tolerance. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the $\epsilon$-$\delta$-IF formulation, which, given a NN and a similarity metric learnt from data, requires that the output difference between any pair of $\epsilon$-similar individuals is bounded by a maximum decision tolerance $\delta \geq 0$. Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN's non-linearities globally over the input space. We encode this computation as the solution of a Mixed-Integer Linear Programming problem and demonstrate that it can be used to compute IF guarantees on four datasets widely used for fairness benchmarking. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.

Related papers

• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• A multiobjective continuation method to compute the regularization path of deep neural networks [1.3654846342364308]
  Sparsity is a highly feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models, and robustness. We present an algorithm that allows for the entire sparse front for the above-mentioned objectives in a very efficient manner for high-dimensional gradients with millions of parameters. We demonstrate that knowledge of the regularization path allows for a well-generalizing network parametrization.
  arXiv  Detail & Related papers  (2023-08-23T10:08:52Z)
• Fast, Distribution-free Predictive Inference for Neural Networks with Coverage Guarantees [25.798057062452443]
  This paper introduces a novel, computationally-efficient algorithm for predictive inference (PI) It requires no distributional assumptions on the data and can be computed faster than existing bootstrap-type methods for neural networks.
  arXiv  Detail & Related papers  (2023-06-11T04:03:58Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Individual Fairness in Bayesian Neural Networks [9.386341375741225]
  We study Individual Fairness (IF) for Bayesian neural networks (BNNs) We use bounds on statistical sampling over the input space and the relationship between adversarial and individual fairness to derive a framework for the robustness estimation of $epsilon$-$delta$-IF. We find that BNNs trained by means of approximate Bayesian inference consistently tend to be markedly more individually fair than their deterministic counterparts.
  arXiv  Detail & Related papers  (2023-04-21T09:12:14Z)
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks [0.0]
  Multiplicative normalizing flows (MNFs) are a family of approximate posteriors for the parameters of BNNs. We have compared MNFs with respect to the standard BNNs, and the flipout estimator. MNFs provide more realistic predictive distribution closer to the true posterior mitigating the bias introduced by the variational approximation.
  arXiv  Detail & Related papers  (2023-01-09T16:07:48Z)
• Log-based Sparse Nonnegative Matrix Factorization for Data Representation [55.72494900138061]
  Nonnegative matrix factorization (NMF) has been widely studied in recent years due to its effectiveness in representing nonnegative data with parts-based representations. We propose a new NMF method with log-norm imposed on the factor matrices to enhance the sparseness. A novel column-wisely sparse norm, named $ell_2,log$-(pseudo) norm, is proposed to enhance the robustness of the proposed method.
  arXiv  Detail & Related papers  (2022-04-22T11:38:10Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Linear Speedup in Personalized Collaborative Learning [69.45124829480106]
  Personalization in federated learning can improve the accuracy of a model for a user by trading off the model's bias. We formalize the personalized collaborative learning problem as optimization of a user's objective. We explore conditions under which we can optimally trade-off their bias for a reduction in variance.
  arXiv  Detail & Related papers  (2021-11-10T22:12:52Z)
• Neural Optimization Kernel: Towards Robust Deep Learning [13.147925376013129]
  Recent studies show a connection between neural networks (NN) and kernel methods. This paper proposes a novel kernel family named Kernel (NOK) We show that over parameterized deep NN (NOK) can increase the expressive power to reduce empirical risk and reduce the bound generalization at the same time.
  arXiv  Detail & Related papers  (2021-06-11T00:34:55Z)

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.