Fairly Accurate: Fairness-aware Multi-group Target Detection in Online Discussion

• URL: http://arxiv.org/abs/2407.11933v2
• Date: Wed, 25 Jun 2025 23:07:40 GMT
• Title: Fairly Accurate: Fairness-aware Multi-group Target Detection in Online Discussion
• Authors: Soumyajit Gupta, Maria De-Arteaga, Matthew Lease,
• Abstract summary: We focus on the fairness implications of target-group detection in the context of toxicity detection.<n>Because toxicity is highly contextual, language that appears benign in general may be harmful when targeting specific demographic groups.<n>We show that our proposed approach to em fairness-aware multi target-group detection achieves competitive predictive performance, outperforming existing fairness-aware baselines.
• Score: 8.812487330632282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Target-group detection is the task of detecting which group(s) a social media post is ``directed at or about'', with various applications, such as targeted-marketing. In this work, we focus on the fairness implications of target-group detection in the context of toxicity detection, where the perceived harm of a post often depends on which group(s) it targets. Because toxicity is highly contextual, language that appears benign in general may be harmful when targeting specific demographic groups. It is thus important to first detect which group(s) are being {\em targeted} by a post as a precursor to the subsequent task of determining whether the post is toxic given the group(s). Target-group detection is also challenging: a single post may simultaneously target one to many groups, and we must detect groups fairly in order to promote equitable treatment. We show that our proposed approach to {\em fairness-aware multi target-group detection} not only reduces bias across groups, but also achieves competitive predictive performance, outperforming existing fairness-aware baselines. To spur future research on fairness-aware target-group detection and support competitive benchmarking, we also share our code.

Related papers

• Quantifying Query Fairness Under Unawareness [82.33181164973365]
  We introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications.<n>Our method outperforms existing baselines across various sensitive attributes and is the first to establish a reliable protocol for measuring fairness under unawareness.
  arXiv  Detail & Related papers  (2025-06-04T16:31:44Z)
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [53.96714099151378]
  We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models. Our method improves its two key components: minority samples identification and the robust training algorithm. Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
  arXiv  Detail & Related papers  (2025-03-12T15:46:12Z)
• Differential Adjusted Parity for Learning Fair Representations [14.267727134658292]
  Development of fair and unbiased machine learning models remains an ongoing objective for researchers in the field of artificial intelligence. We introduce the Differential Adjusted Parity (DAP) loss to produce unbiased informative representations.
  arXiv  Detail & Related papers  (2025-02-13T20:48:26Z)
• Generalization bounds for regression and classification on adaptive covering input domains [1.4141453107129398]
  We focus on the generalization bound, which serves as an upper limit for the generalization error. In the case of classification tasks, we treat the target function as a one-hot, a piece-wise constant function, and employ 0/1 loss for error measurement.
  arXiv  Detail & Related papers  (2024-07-29T05:40:08Z)
• Hate Speech Detection with Generalizable Target-aware Fairness [31.019324291704628]
  Generalizable target-aware Fairness (GetFair) is a new method for fairly classifying each post that contains diverse and even unseen targets during inference. GetFair trains a series of filter functions in an adversarial pipeline, so as to deceive the discriminator. Experiments on two HSD datasets have shown advantageous performance of GetFair on out-of-sample targets.
  arXiv  Detail & Related papers  (2024-05-28T13:09:22Z)
• Unveiling Social Media Comments with a Novel Named Entity Recognition System for Identity Groups [2.5849042763002426]
  We develop a Named Entity Recognition (NER) System for Identity Groups. Our tool not only detects whether a sentence contains an attack but also tags the sentence tokens corresponding to the mentioned group. We tested the utility of our tool in a case study on social media, annotating and comparing comments from Facebook related to news mentioning identity groups.
  arXiv  Detail & Related papers  (2024-05-13T19:33:18Z)
• A Canonical Data Transformation for Achieving Inter- and Within-group Fairness [17.820200610132265]
  We introduce a formal definition of within-group fairness that maintains fairness among individuals from within the same group. We propose a pre-processing framework to meet both inter- and within-group fairness criteria with little compromise in accuracy. We apply this framework to the COMPAS risk assessment and Law School datasets and compare its performance to two regularization-based methods.
  arXiv  Detail & Related papers  (2023-10-23T17:00:20Z)
• Bridging the Gap Between Target Networks and Functional Regularization [61.051716530459586]
  We propose an explicit Functional Regularization that is a convex regularizer in function space and can easily be tuned. We analyze the convergence of our method theoretically and empirically demonstrate that replacing Target Networks with the more theoretically grounded Functional Regularization approach leads to better sample efficiency and performance improvements.
  arXiv  Detail & Related papers  (2022-10-21T22:27:07Z)
• AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection [59.10314662986463]
  Cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. The proposed method achieves state-of-the-art performance on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-09-22T10:23:40Z)
• Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection [19.940491797959407]
  In this work, we revisit the average precision (AP)loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. We propose two strategies to improve the AP loss. The first is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Experiments conducted on the MSCOCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss.
  arXiv  Detail & Related papers  (2022-07-25T10:33:06Z)
• Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection [13.26226951002133]
  This paper addresses the challenges of defining, approximating, and utilizing a new subgroup structure for fair spam detection. We first identify subgroup structures in the review graph that lead to discrepant accuracy in the groups. Comprehensive comparisons against baselines on three large Yelp review datasets demonstrate that the subgroup membership can be identified and exploited for group fairness.
  arXiv  Detail & Related papers  (2022-04-24T02:19:22Z)
• Towards Group Robustness in the presence of Partial Group Labels [61.33713547766866]
  spurious correlations between input samples and the target labels wrongly direct the neural network predictions. We propose an algorithm that optimize for the worst-off group assignments from a constraint set. We show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.
  arXiv  Detail & Related papers  (2022-01-10T22:04:48Z)
• Searching Parameterized AP Loss for Object Detection [36.3603004789312]
  Loss functions play an important role in training deep-network-based object detectors. Due to the non-differentiable nature of the AP metric, traditional object detectors adopt separate differentiable losses for the two sub-tasks. We propose parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
  arXiv  Detail & Related papers  (2021-12-09T18:59:54Z)
• Reducing Target Group Bias in Hate Speech Detectors [56.94616390740415]
  We show that text classification models trained on large publicly available datasets, may significantly under-perform on several protected groups. We propose to perform token-level hate sense disambiguation, and utilize tokens' hate sense representations for detection.
  arXiv  Detail & Related papers  (2021-12-07T17:49:34Z)
• Focus on the Common Good: Group Distributional Robustness Follows [47.62596240492509]
  This paper proposes a new and simple algorithm that explicitly encourages learning of features that are shared across various groups. While Group-DRO focuses on groups with worst regularized loss, focusing instead, on groups that enable better performance even on other groups, could lead to learning of shared/common features.
  arXiv  Detail & Related papers  (2021-10-06T09:47:41Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• Costs and Benefits of Wasserstein Fair Regression [11.134279147254361]
  In this paper, we characterize the inherent tradeoff between statistical parity and accuracy in the regression setting. Our lower bound is sharp, algorithm-independent, and admits a simple interpretation. We develop a practical algorithm for fair regression through the lens of representation learning.
  arXiv  Detail & Related papers  (2021-06-16T14:24:44Z)
• KL Guided Domain Adaptation [88.19298405363452]
  Domain adaptation is an important problem and often needed for real-world applications. A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
  arXiv  Detail & Related papers  (2021-06-14T22:24:23Z)
• Fair Clustering Under a Bounded Cost [33.50262066253557]
  Clustering is a fundamental unsupervised learning problem where a dataset is partitioned into clusters that consist of nearby points in a metric space. A recent variant, fair clustering, associates a color with each point representing its group membership and requires that each color has (approximately) equal representation in each cluster to satisfy group fairness. We consider two fairness objectives: the group utilitarian objective and the group egalitarian objective, as well as the group leximin objective which generalizes the group egalitarian objective.
  arXiv  Detail & Related papers  (2021-06-14T08:47:36Z)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)
• 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)
• Learning a Unified Sample Weighting Network for Object Detection [113.98404690619982]
  Region sampling or weighting is significantly important to the success of modern region-based object detectors. We argue that sample weighting should be data-dependent and task-dependent. We propose a unified sample weighting network to predict a sample's task weights.
  arXiv  Detail & Related papers  (2020-06-11T16:19:16Z)
• Robust Optimization for Fairness with Noisy Protected Groups [85.13255550021495]
  We study the consequences of naively relying on noisy protected group labels. We introduce two new approaches using robust optimization. We show that the robust approaches achieve better true group fairness guarantees than the naive approach.
  arXiv  Detail & Related papers  (2020-02-21T14:58:37Z)

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.