Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

• URL: http://arxiv.org/abs/2106.09788v1
• Date: Thu, 17 Jun 2021 20:00:55 GMT
• Title: Guided Integrated Gradients: An Adaptive Path Method for Removing Noise
• Authors: Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, Tolga Bolukbasi
• Abstract summary: Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. We show that one of the causes of the problem is the accumulation of noise along the IG path. We propose adapting the attribution path itself -- conditioning the path not just on the image but also on the model being explained.
• Score: 9.792727625917083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are not related to the predicted class when applied to visual models. While this has been previously noted, most existing solutions are aimed at addressing the symptoms by explicitly reducing the noise in the resulting attributions. In this work, we show that one of the causes of the problem is the accumulation of noise along the IG path. To minimize the effect of this source of noise, we propose adapting the attribution path itself -- conditioning the path not just on the image but also on the model being explained. We introduce Adaptive Path Methods (APMs) as a generalization of path methods, and Guided IG as a specific instance of an APM. Empirically, Guided IG creates saliency maps better aligned with the model's prediction and the input image that is being explained. We show through qualitative and quantitative experiments that Guided IG outperforms other, related methods in nearly every experiment.

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)
• GeoGuide: Geometric guidance of diffusion models [8.34616719984217]
  GeoGuide is a guidance model based on tracing the distance of the diffusion model's trajectory from the data manifold. It surpasses the probabilistic approach ADM-G with respect to both the FID scores and the quality of the generated images.
  arXiv  Detail & Related papers  (2024-07-17T07:56:27Z)
• IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution [6.278326325782819]
  Iterative Gradient path Integrated Gradients (IG2) is a prominent path attribution method for deep neural networks. IG2 incorporates the counterfactual gradient iteratively into the integration path, generating a novel path (GradPath) and a novel baseline (GradCF) Experimental results on XAI benchmark, ImageNet, MNIST, TREC questions answering, wafer-map failure patterns, and CelebA face attributes validate that IG2 delivers superior feature attributions.
  arXiv  Detail & Related papers  (2024-06-16T08:48:03Z)
• Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms [88.74308282658133]
  Reization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. Recent studies have revealed that, when applied to long-term reinforcement learning problems, model-based RP PGMs may experience chaotic and non-smooth optimization landscapes. We propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls.
  arXiv  Detail & Related papers  (2023-10-30T18:43:21Z)
• Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters [69.24377241408851]
  Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. We propose to base the selection on gradient-signal-to-noise ratio (GSNR) of network's parameters.
  arXiv  Detail & Related papers  (2023-10-11T10:21:34Z)
• Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation [40.18851174642427]
  Deep neural networks are vulnerable to universal adversarial perturbation (UAP) In this paper, we examine the serious dilemma of UAP generation methods from a generalization perspective. We propose a simple and effective method called Gradient Aggregation (SGA) SGA alleviates the gradient vanishing and escapes from poor local optima at the same time.
  arXiv  Detail & Related papers  (2023-08-11T08:44:58Z)
• Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision [9.385886214196479]
  We propose an attribution algorithm called integrated decision gradients (IDG) IDG focuses on integrating gradients from the region of the path where the model makes its decision, i.e., the portion of the path where the output logit rapidly transitions from zero to its final value. We minimize the errors within the sum approximation of the path integral by utilizing non-uniform subdivisions determined by adaptive sampling.
  arXiv  Detail & Related papers  (2023-05-31T17:25:12Z)
• Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
  Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
  arXiv  Detail & Related papers  (2020-08-25T03:30:53Z)
• Shape Matters: Understanding the Implicit Bias of the Noise Covariance [76.54300276636982]
  Noise in gradient descent provides a crucial implicit regularization effect for training over parameterized models. We show that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not.
  arXiv  Detail & Related papers  (2020-06-15T18:31:02Z)
• On Noise Injection in Generative Adversarial Networks [85.51169466453646]
  Noise injection has been proved to be one of the key technique advances in generating high-fidelity images. We propose a geometric framework to theoretically analyze the role of noise injection in GANs.
  arXiv  Detail & Related papers  (2020-06-10T15:24:48Z)
• Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution [70.78655569298923]
  Integrated Gradients as an attribution method for deep neural network models offers simple implementability. It suffers from noisiness of explanations which affects the ease of interpretability. The SmoothGrad technique is proposed to solve the noisiness issue and smoothen the attribution maps of any gradient-based attribution method.
  arXiv  Detail & Related papers  (2020-04-22T10:43:19Z)

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.