NoiseGrad: enhancing explanations by introducing stochasticity to model weights

• URL: http://arxiv.org/abs/2106.10185v1
• Date: Fri, 18 Jun 2021 15:22:33 GMT
• Title: NoiseGrad: enhancing explanations by introducing stochasticity to model weights
• Authors: Kirill Bykov, Anna Hedstr\"om, Shinichi Nakajima, Marina M.-C. H\"ohne
• Abstract summary: NoiseGrad is a method-agnostic explanation-enhancing method that adds noise to the weights instead of the input data. We investigate our proposed method through various experiments including different datasets.
• Score: 4.735227614605093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Attribution methods remain a practical instrument that is used in real-world applications to explain the decision-making process of complex learning machines. It has been shown that a simple method called SmoothGrad can effectively reduce the visual diffusion of gradient-based attribution methods and has established itself among both researchers and practitioners. What remains unexplored in research, however, is how explanations can be improved by introducing stochasticity to the model weights. In the light of this, we introduce - NoiseGrad - a stochastic, method-agnostic explanation-enhancing method that adds noise to the weights instead of the input data. We investigate our proposed method through various experiments including different datasets, explanation methods and network architectures and conclude that NoiseGrad (and its extension NoiseGrad++) with multiplicative Gaussian noise offers a clear advantage compared to SmoothGrad on several evaluation criteria. We connect our proposed method to Bayesian Learning and provide the user with a heuristic for choosing hyperparameters.

Related papers

• Rethinking the Principle of Gradient Smooth Methods in Model Explanation [2.6819730646697972]
  Gradient Smoothing is an efficient approach to reducing noise in gradient-based model explanation method. We propose an adaptive gradient smoothing method, AdaptGrad, based on these insights.
  arXiv  Detail & Related papers  (2024-10-10T08:24:27Z)
• Blue noise for diffusion models [50.99852321110366]
  We introduce a novel and general class of diffusion models taking correlated noise within and across images into account. Our framework allows introducing correlation across images within a single mini-batch to improve gradient flow. We perform both qualitative and quantitative evaluations on a variety of datasets using our method.
  arXiv  Detail & Related papers  (2024-02-07T14:59:25Z)
• Learning minimal representations of stochastic processes with variational autoencoders [52.99137594502433]
  We introduce an unsupervised machine learning approach to determine the minimal set of parameters required to describe a process. Our approach enables for the autonomous discovery of unknown parameters describing processes.
  arXiv  Detail & Related papers  (2023-07-21T14:25:06Z)
• Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty [8.815974147041048]
  We develop a novel framework to identify parsimonious governing equations of nonlinear (spatiotemporal) dynamics from sparse, noisy data with quantified uncertainty. The proposed algorithm is evaluated on multiple nonlinear dynamical systems governed by canonical ordinary and partial differential equations.
  arXiv  Detail & Related papers  (2022-10-14T20:37:36Z)
• On the Theoretical Properties of Noise Correlation in Stochastic Optimization [6.970991851511823]
  We show that fPGD possesses exploration abilities favorable over PGD and Anti-PGD. These results open the field to novel ways to exploit noise for machine learning models.
  arXiv  Detail & Related papers  (2022-09-19T16:32:22Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Deep Active Learning with Noise Stability [24.54974925491753]
  Uncertainty estimation for unlabeled data is crucial to active learning. We propose a novel algorithm that leverages noise stability to estimate data uncertainty. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis.
  arXiv  Detail & Related papers  (2022-05-26T13:21:01Z)
• Robust Imitation Learning from Noisy Demonstrations [81.67837507534001]
  We show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. We propose a new imitation learning method that effectively combines pseudo-labeling with co-training. Experimental results on continuous-control benchmarks show that our method is more robust compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-20T10:41:37Z)
• Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks [85.94999581306827]
  Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights. Many successful experimental results have been achieved with empirical straight-through (ST) approaches. At the same time, ST methods can be truly derived as estimators in the binary network (SBN) model with Bernoulli weights.
  arXiv  Detail & Related papers  (2020-06-11T23:58:18Z)
• There and Back Again: Revisiting Backpropagation Saliency Methods [87.40330595283969]
  Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. We propose a single framework under which several such methods can be unified.
  arXiv  Detail & Related papers  (2020-04-06T17:58:08Z)

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.