Elastic weight consolidation for better bias inoculation

• URL: http://arxiv.org/abs/2004.14366v2
• Date: Thu, 4 Feb 2021 10:57:26 GMT
• Title: Elastic weight consolidation for better bias inoculation
• Authors: James Thorne, Andreas Vlachos
• Abstract summary: Elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases. EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset.
• Score: 24.12790037712358
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate them, a common issue is that of catastrophic forgetting of the original training dataset. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases while being less susceptible to catastrophic forgetting. In our evaluation on fact verification and NLI stress tests, we show that fine-tuning with EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset for equivalent gains in accuracy on the fine-tuning (unbiased) dataset.

Related papers

• Does Data-Efficient Generalization Exacerbate Bias in Foundation Models? [2.298227866545911]
  Foundation models have emerged as robust models with label efficiency in diverse domains. It is unclear whether using a large amount of unlabeled data, biased by the presence of sensitive attributes during pre-training, influences the fairness of the model. This research examines the bias in the Foundation model when it is applied to fine-tune the Brazilian Multilabel Ophthalmological dataset.
  arXiv  Detail & Related papers  (2024-08-28T22:14:44Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models [31.84120883461332]
  We analyze the robustness of fine-tuning based summarization models to the knowledge conflict. We introduce a controllable counterfactual data augmentation method.
  arXiv  Detail & Related papers  (2024-02-23T07:53:39Z)
• Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection [82.43311784594384]
  Real-world datasets contain not only noisy labels but also class imbalance. We propose a simple yet effective method to address noisy labels in imbalanced datasets.
  arXiv  Detail & Related papers  (2024-02-17T10:34:53Z)
• Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models [75.9543301303586]
  Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that prior work has overlooked the inherent biases in foundation models.
  arXiv  Detail & Related papers  (2023-10-12T08:01:11Z)
• Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases [5.997909991352044]
  Recent work sought to develop robust, unbiased models by filtering biased examples from training sets. We argue that such filtering can obscure the true capabilities of models to overcome biases. We introduce an evaluation framework defined by a bias-amplified training set and an anti-biased test set.
  arXiv  Detail & Related papers  (2023-05-30T10:10:42Z)
• Overwriting Pretrained Bias with Finetuning Data [36.050345384273655]
  We investigate bias when conceptualized as both spurious correlations between the target task and a sensitive attribute as well as underrepresentation of a particular group in the dataset. We find that models finetuned on top of pretrained models can indeed inherit their biases, but (2) this bias can be corrected for through relatively minor interventions to the finetuning dataset. Our findings imply that careful curation of the finetuning dataset is important for reducing biases on a downstream task, and doing so can even compensate for bias in the pretrained model.
  arXiv  Detail & Related papers  (2023-03-10T19:10:58Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• Certifying Data-Bias Robustness in Linear Regression [12.00314910031517]
  We present a technique for certifying whether linear regression models are pointwise-robust to label bias in a training dataset. We show how to solve this problem exactly for individual test points, and provide an approximate but more scalable method. We also unearth gaps in bias-robustness, such as high levels of non-robustness for certain bias assumptions on some datasets.
  arXiv  Detail & Related papers  (2022-06-07T20:47:07Z)
• Towards Robustifying NLI Models Against Lexical Dataset Biases [94.79704960296108]
  This paper explores both data-level and model-level debiasing methods to robustify models against lexical dataset biases. First, we debias the dataset through data augmentation and enhancement, but show that the model bias cannot be fully removed via this method. The second approach employs a bag-of-words sub-model to capture the features that are likely to exploit the bias and prevents the original model from learning these biased features.
  arXiv  Detail & Related papers  (2020-05-10T17:56:10Z)

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.