Gradients as a Measure of Uncertainty in Neural Networks

• URL: http://arxiv.org/abs/2008.08030v2
• Date: Thu, 3 Sep 2020 19:47:36 GMT
• Title: Gradients as a Measure of Uncertainty in Neural Networks
• Authors: Jinsol Lee and Ghassan AlRegib
• Abstract summary: We propose to utilize backpropagated gradients to quantify the uncertainty of trained models. We show that our gradient-based method outperforms state-of-the-art methods by up to 4.8% of AUROC score in out-of-distribution detection.
• Score: 16.80077149399317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is vital to preventing models from making naive predictions that may jeopardize real-world applications of neural networks. In this paper, we address the challenging problem of devising a simple yet effective measure of uncertainty in deep neural networks. Specifically, we propose to utilize backpropagated gradients to quantify the uncertainty of trained models. Gradients depict the required amount of change for a model to properly represent given inputs, thus providing a valuable insight into how familiar and certain the model is regarding the inputs. We demonstrate the effectiveness of gradients as a measure of model uncertainty in applications of detecting unfamiliar inputs, including out-of-distribution and corrupted samples. We show that our gradient-based method outperforms state-of-the-art methods by up to 4.8% of AUROC score in out-of-distribution detection and 35.7% in corrupted input detection.

Related papers

• Epistemic Uncertainty Quantification For Pre-trained Neural Network [27.444465823508715]
  Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained non-Bayesian models.
  arXiv  Detail & Related papers  (2024-04-15T20:21:05Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Probing the Purview of Neural Networks via Gradient Analysis [13.800680101300756]
  We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. To probe the purview of a network, we utilize gradients to measure the amount of change required for the model to characterize the given inputs more accurately. We demonstrate that our gradient-based approach can effectively differentiate inputs that cannot be accurately represented with learned features.
  arXiv  Detail & Related papers  (2023-04-06T03:02:05Z)
• Model2Detector:Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps [12.263417500077383]
  Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Recent advances in inference-time out-of-distribution detection help mitigate some of these problems. We show how our method consistently outperforms the state-of-the-art in detection accuracy on popular image datasets.
  arXiv  Detail & Related papers  (2022-02-22T23:03:40Z)
• RoMA: a Method for Neural Network Robustness Measurement and Assessment [0.0]
  We present a new statistical method, called Robustness Measurement and Assessment (RoMA) RoMA determines the probability that a random input perturbation might cause misclassification. One interesting insight obtained through this work is that, in a classification network, different output labels can exhibit very different robustness levels.
  arXiv  Detail & Related papers  (2021-10-21T12:01:54Z)
• Residual Error: a New Performance Measure for Adversarial Robustness [85.0371352689919]
  A major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversarial attacks. This study presents the concept of residual error, a new performance measure for assessing the adversarial robustness of a deep neural network. Experimental results using the case of image classification demonstrate the effectiveness and efficacy of the proposed residual error metric.
  arXiv  Detail & Related papers  (2021-06-18T16:34:23Z)
• 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)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings [7.476901945542385]
  We show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks. Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions.
  arXiv  Detail & Related papers  (2020-09-03T16:58:15Z)
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network [66.26231423824089]
  We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models.
  arXiv  Detail & Related papers  (2020-03-04T12:27:36Z)

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.