Soft-Label Integration for Robust Toxicity Classification

• URL: http://arxiv.org/abs/2410.14894v2
• Date: Thu, 07 Nov 2024 21:53:17 GMT
• Title: Soft-Label Integration for Robust Toxicity Classification
• Authors: Zelei Cheng, Xian Wu, Jiahao Yu, Shuo Han, Xin-Qiang Cai, Xinyu Xing,
• Abstract summary: This work introduces a novel bi-level optimization framework that integrates crowdsourced annotations with the soft-labeling technique. GroupDRO is used to enhance the robustness against out-of-distribution (OOD) risk. Experimental results demonstrate that our approach outperforms existing baseline methods in terms of both average and worst-group accuracy.
• Score: 39.159343518702805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Toxicity classification in textual content remains a significant problem. Data with labels from a single annotator fall short of capturing the diversity of human perspectives. Therefore, there is a growing need to incorporate crowdsourced annotations for training an effective toxicity classifier. Additionally, the standard approach to training a classifier using empirical risk minimization (ERM) may fail to address the potential shifts between the training set and testing set due to exploiting spurious correlations. This work introduces a novel bi-level optimization framework that integrates crowdsourced annotations with the soft-labeling technique and optimizes the soft-label weights by Group Distributionally Robust Optimization (GroupDRO) to enhance the robustness against out-of-distribution (OOD) risk. We theoretically prove the convergence of our bi-level optimization algorithm. Experimental results demonstrate that our approach outperforms existing baseline methods in terms of both average and worst-group accuracy, confirming its effectiveness in leveraging crowdsourced annotations to achieve more effective and robust toxicity classification.

Related papers

• Re-evaluating Group Robustness via Adaptive Class-Specific Scaling [47.41034887474166]
  Group distributionally robust optimization is a prominent algorithm used to mitigate spurious correlations and address dataset bias. Existing approaches have reported improvements in robust accuracies but come at the cost of average accuracy due to inherent trade-offs. We propose a class-specific scaling strategy, directly applicable to existing debiasing algorithms with no additional training. We develop an instance-wise adaptive scaling technique to alleviate this trade-off, even leading to improvements in both robust and average accuracies.
  arXiv  Detail & Related papers  (2024-12-19T16:01:51Z)
• Learning from Noisy Labels via Conditional Distributionally Robust Optimization [5.85767711644773]
  crowdsourcing has emerged as a practical solution for labeling large datasets. It presents a significant challenge in learning accurate models due to noisy labels from annotators with varying levels of expertise.
  arXiv  Detail & Related papers  (2024-11-26T05:03:26Z)
• Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning [81.83013974171364]
  Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most probable label as the pseudo-label in SSMLL due to multiple semantics contained in an instance. We propose a dual-perspective method to generate high-quality pseudo-labels.
  arXiv  Detail & Related papers  (2024-07-26T09:33:53Z)
• DRoP: Distributionally Robust Pruning [11.930434318557156]
  We conduct the first systematic study of the impact of data pruning on classification bias of trained models. We propose DRoP, a distributionally robust approach to pruning and empirically demonstrate its performance on standard computer vision benchmarks.
  arXiv  Detail & Related papers  (2024-04-08T14:55:35Z)
• Group Robust Classification Without Any Group Information [5.053622900542495]
  This study contends that current bias-unsupervised approaches to group robustness continue to rely on group information to achieve optimal performance. bias labels are still crucial for effective model selection, restricting the practicality of these methods in real-world scenarios. We propose a revised methodology for training and validating debiased models in an entirely bias-unsupervised manner.
  arXiv  Detail & Related papers  (2023-10-28T01:29:18Z)
• Doubly Robust Instance-Reweighted Adversarial Training [107.40683655362285]
  We propose a novel doubly-robust instance reweighted adversarial framework. Our importance weights are obtained by optimizing the KL-divergence regularized loss function. Our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance.
  arXiv  Detail & Related papers  (2023-08-01T06:16:18Z)
• Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization [61.39201891894024]
  Group distributionally robust optimization (group DRO) can minimize the worst-case loss over pre-defined groups. We reformulate the group DRO framework by proposing Q-Diversity. Characterized by an interactive training mode, Q-Diversity relaxes the group identification from annotation into direct parameterization.
  arXiv  Detail & Related papers  (2023-05-20T07:02:27Z)
• SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning [101.86916775218403]
  This paper revisits the popular pseudo-labeling methods via a unified sample weighting formulation. We propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.
  arXiv  Detail & Related papers  (2023-01-26T03:53:25Z)
• Distributionally Robust Learning with Stable Adversarial Training [34.74504615726101]
  Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts. We propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set.
  arXiv  Detail & Related papers  (2021-06-30T03:05:45Z)
• Delving Deep into Label Smoothing [112.24527926373084]
  Label smoothing is an effective regularization tool for deep neural networks (DNNs) We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category.
  arXiv  Detail & Related papers  (2020-11-25T08:03:11Z)
• Stable Adversarial Learning under Distributional Shifts [46.98655899839784]
  Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts. We propose Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set.
  arXiv  Detail & Related papers  (2020-06-08T08:42:34Z)

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.