Balancing Robustness and Sensitivity using Feature Contrastive Learning

• URL: http://arxiv.org/abs/2105.09394v1
• Date: Wed, 19 May 2021 20:53:02 GMT
• Title: Balancing Robustness and Sensitivity using Feature Contrastive Learning
• Authors: Seungyeon Kim, Daniel Glasner, Srikumar Ramalingam, Cho-Jui Hsieh, Kishore Papineni, Sanjiv Kumar
• Abstract summary: Methods that promote robustness can hurt the model's sensitivity to rare or underrepresented patterns. We propose Feature Contrastive Learning (FCL) that encourages a model to be more sensitive to the features that have higher contextual utility.
• Score: 95.86909855412601
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that promote robustness can hurt the model's sensitivity to rare or underrepresented patterns. In this paper, we discuss this trade-off between sensitivity and robustness to natural (non-adversarial) perturbations by introducing two notions: contextual feature utility and contextual feature sensitivity. We propose Feature Contrastive Learning (FCL) that encourages a model to be more sensitive to the features that have higher contextual utility. Empirical results demonstrate that models trained with FCL achieve a better balance of robustness and sensitivity, leading to improved generalization in the presence of noise on both vision and NLP datasets.

Related papers

• ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs [72.13489820420726]
  ProSA is a framework designed to evaluate and comprehend prompt sensitivity in large language models. Our study uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness.
  arXiv  Detail & Related papers  (2024-10-16T09:38:13Z)
• Evaluating and Improving Continual Learning in Spoken Language Understanding [58.723320551761525]
  We propose an evaluation methodology that provides a unified evaluation on stability, plasticity, and generalizability in continual learning. By employing the proposed metric, we demonstrate how introducing various knowledge distillations can improve different aspects of these three properties of the SLU model.
  arXiv  Detail & Related papers  (2024-02-16T03:30:27Z)
• How are Prompts Different in Terms of Sensitivity? [50.67313477651395]
  We present a comprehensive prompt analysis based on the sensitivity of a function. We use gradient-based saliency scores to empirically demonstrate how different prompts affect the relevance of input tokens to the output. We introduce sensitivity-aware decoding which incorporates sensitivity estimation as a penalty term in the standard greedy decoding.
  arXiv  Detail & Related papers  (2023-11-13T10:52:01Z)
• Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability Connection [0.0]
  Interpretability is as essential as robustness when we deploy the models to the real world. Standard models, compared to robust are more susceptible to adversarial attacks, and their learned representations are less meaningful to humans.
  arXiv  Detail & Related papers  (2023-07-04T13:51:55Z)
• On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training [109.9218185711916]
  Aspect-based sentiment analysis (ABSA) aims at automatically inferring the specific sentiment polarities toward certain aspects of products or services behind social media texts or reviews. We propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data, and training.
  arXiv  Detail & Related papers  (2023-04-19T11:07:43Z)
• Improving Interpretability via Regularization of Neural Activation Sensitivity [20.407987149443997]
  State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. They are susceptible to adversarial attacks and their opaqueness impedes users' trust in their output. We present a novel approach for improving the interpretability of DNNs based on regularization of neural activation sensitivity.
  arXiv  Detail & Related papers  (2022-11-16T05:40:29Z)
• Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness [17.5771010094384]
  Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. Recent work argues the adversarial vulnerability of the model is caused by the non-robust features in supervised training. In this paper, we tackle the adversarial challenge from the view of disentangled representation learning.
  arXiv  Detail & Related papers  (2022-10-26T18:14:39Z)
• Causally Estimating the Sensitivity of Neural NLP Models to Spurious Features [19.770032728328733]
  There is no measure to evaluate or compare the effects of different forms of spurious features in NLP. We quantify model sensitivity to spurious features with a causal estimand, dubbed CENT. We find statistically significant inverse correlations between sensitivity and robustness, providing empirical support for our hypothesis.
  arXiv  Detail & Related papers  (2021-10-14T05:26:08Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)

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.