TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination

• URL: http://arxiv.org/abs/2208.11321v1
• Date: Wed, 24 Aug 2022 06:26:06 GMT
• Title: TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination
• Authors: Mengdi Zhang and Jun Sun and Jingyi Wang and Bing Sun
• Abstract summary: We propose TESTSGD, an interpretable testing approach which systematically identifies and measures hidden group discrimination. We evaluate TESTSGD on popular datasets including both structured data and text data.
• Score: 8.207802966970378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing fairness testing approaches are mostly designed for identifying individual discrimination, i.e., discrimination against individuals. Yet, as another widely concerning type of discrimination, testing against group discrimination, mostly hidden, is much less studied. To address the gap, in this work, we propose TESTSGD, an interpretable testing approach which systematically identifies and measures hidden (which we call `subtle' group discrimination} of a neural network characterized by conditions over combinations of the sensitive features. Specifically, given a neural network, TESTSGDfirst automatically generates an interpretable rule set which categorizes the input space into two groups exposing the model's group discrimination. Alongside, TESTSGDalso provides an estimated group fairness score based on sampling the input space to measure the degree of the identified subtle group discrimination, which is guaranteed to be accurate up to an error bound. We evaluate TESTSGDon multiple neural network models trained on popular datasets including both structured data and text data. The experiment results show that TESTSGDis effective and efficient in identifying and measuring such subtle group discrimination that has never been revealed before. Furthermore, we show that the testing results of TESTSGDcan guide generation of new samples to mitigate such discrimination through retraining with negligible accuracy drop.

Related papers

• GroupMixNorm Layer for Learning Fair Models [4.324785083027206]
  This research proposes a novel in-processing based GroupMixNorm layer for mitigating bias from deep learning models. The proposed method improves upon several fairness metrics with minimal impact on overall accuracy.
  arXiv  Detail & Related papers  (2023-12-19T09:04:26Z)
• Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment [87.8301166955305]
  We propose a novel bi-discriminator domain adversarial neural network with class-level gradient alignment. BACG resorts to gradient signals and second-order probability estimation for better alignment of domain distributions. In addition, inspired by contrastive learning, we develop a memory bank-based variant, i.e. Fast-BACG, which can greatly shorten the training process.
  arXiv  Detail & Related papers  (2023-10-21T09:53:17Z)
• Population-Based Evolutionary Gaming for Unsupervised Person Re-identification [26.279581599246224]
  Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. We develop a population-based evolutionary gaming (PEG) framework in which a population of diverse neural networks is trained concurrently through selection, reproduction, mutation, and population mutual learning. PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning.
  arXiv  Detail & Related papers  (2023-06-08T14:33:41Z)
• Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions [13.279926364884512]
  Machine learning models can underperform on certain population groups due to choices made during model development and bias inherent in the data. We quantify aleatoric discrimination by determining the performance limits of a model under fairness constraints. We quantify epistemic discrimination as the gap between a model's accuracy when fairness constraints are applied and the limit posed by aleatoric discrimination.
  arXiv  Detail & Related papers  (2023-01-27T15:38:20Z)
• Error Parity Fairness: Testing for Group Fairness in Regression Tasks [5.076419064097733]
  This work presents error parity as a regression fairness notion and introduces a testing methodology to assess group fairness. It is followed by a suitable permutation test to compare groups on several statistics to explore disparities and identify impacted groups. Overall, the proposed regression fairness testing methodology fills a gap in the fair machine learning literature and may serve as a part of larger accountability assessments and algorithm audits.
  arXiv  Detail & Related papers  (2022-08-16T17:47:20Z)
• Statistical and Computational Phase Transitions in Group Testing [73.55361918807883]
  We study the group testing problem where the goal is to identify a set of k infected individuals carrying a rare disease. We consider two different simple random procedures for assigning individuals tests.
  arXiv  Detail & Related papers  (2022-06-15T16:38:50Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• The Group Loss++: A deeper look into group loss for deep metric learning [65.19665861268574]
  Group Loss is a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group. We show state-of-the-art results on clustering and image retrieval on four datasets, and present competitive results on two person re-identification datasets.
  arXiv  Detail & Related papers  (2022-04-04T14:09:58Z)
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning [16.77134235390429]
  Key challenge of OOD detection is to learn discriminative semantic features. We propose a supervised contrastive learning objective to minimize intra-class variance. We employ an adversarial augmentation mechanism to obtain pseudo diverse views of a sample.
  arXiv  Detail & Related papers  (2021-05-29T12:54:22Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)
• Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
  This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
  arXiv  Detail & Related papers  (2020-06-13T06:43:37Z)

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.