Should We Attend More or Less? Modulating Attention for Fairness

• URL: http://arxiv.org/abs/2305.13088v2
• Date: Fri, 2 Aug 2024 19:20:25 GMT
• Title: Should We Attend More or Less? Modulating Attention for Fairness
• Authors: Abdelrahman Zayed, Goncalo Mordido, Samira Shabanian, Sarath Chandar,
• Abstract summary: We study the role of attention, a widely-used technique in current state-of-the-art NLP models, in the propagation of social biases. We propose a novel method for modulating attention weights to improve model fairness after training. Our results show an increase in fairness and minimal performance loss on different text classification and generation tasks.
• Score: 11.91250446389124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advances in natural language processing (NLP) pose both opportunities and challenges. While recent progress enables the development of high-performing models for a variety of tasks, it also poses the risk of models learning harmful biases from the data, such as gender stereotypes. In this work, we investigate the role of attention, a widely-used technique in current state-of-the-art NLP models, in the propagation of social biases. Specifically, we study the relationship between the entropy of the attention distribution and the model's performance and fairness. We then propose a novel method for modulating attention weights to improve model fairness after training. Since our method is only applied post-training and pre-inference, it is an intra-processing method and is, therefore, less computationally expensive than existing in-processing and pre-processing approaches. Our results show an increase in fairness and minimal performance loss on different text classification and generation tasks using language models of varying sizes. WARNING: This work uses language that is offensive.

Related papers

• Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
  We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
  arXiv  Detail & Related papers  (2024-10-02T07:14:26Z)
• Observational Scaling Laws and the Predictability of Language Model Performance [51.2336010244645]
  We propose an observational approach that bypasses model training and instead builds scaling laws from 100 publically available models. We show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models. We show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
  arXiv  Detail & Related papers  (2024-05-17T17:49:44Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)
• The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing [0.043512163406552]
  This study introduces a novel method called "The Fairness Stitch" to enhance fairness in deep learning models. We conduct a comprehensive evaluation of two well-known datasets, CelebA and UTKFace. Our findings reveal a notable improvement in achieving a balanced trade-off between fairness and performance.
  arXiv  Detail & Related papers  (2023-11-06T21:14:37Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• Modeling Techniques for Machine Learning Fairness: A Survey [17.925809181329015]
  In recent years, various techniques have been developed to mitigate the bias for machine learning models. In this survey, we review the current progress of in-processing bias mitigation techniques.
  arXiv  Detail & Related papers  (2021-11-04T17:17:26Z)
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift [10.990447273771592]
  The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications. It builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. It is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime
  arXiv  Detail & Related papers  (2021-09-03T14:29:20Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Learning from others' mistakes: Avoiding dataset biases without modeling them [111.17078939377313]
  State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We show a method for training models that learn to ignore these problematic correlations.
  arXiv  Detail & Related papers  (2020-12-02T16:10:54Z)
• FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret [42.66567001275493]
  It is now accepted that because of biases in the datasets we present to the models, a fairness-oblivious training will lead to unfair models. Here, we study mechanisms that impose fairness concurrently while training the model.
  arXiv  Detail & Related papers  (2020-04-03T03:18:53Z)

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.