Geometrically Guided Integrated Gradients

• URL: http://arxiv.org/abs/2206.05903v1
• Date: Mon, 13 Jun 2022 05:05:43 GMT
• Title: Geometrically Guided Integrated Gradients
• Authors: Md Mahfuzur Rahman, Noah Lewis, Sergey Plis
• Abstract summary: We introduce an interpretability method called "geometrically-guided integrated gradients" Our method explores the model's dynamic behavior from multiple scaled versions of the input and captures the best possible attribution for each input. We also propose a "model perturbation" sanity check to complement the traditionally used "model randomization" test.
• Score: 0.3867363075280543
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also use a model-agnostic approach to understanding the rationale behind every prediction. In this paper, we argue and demonstrate that local geometry of the model parameter space relative to the input can also be beneficial for improved post-hoc explanations. To achieve this goal, we introduce an interpretability method called "geometrically-guided integrated gradients" that builds on top of the gradient calculation along a linear path as traditionally used in integrated gradient methods. However, instead of integrating gradient information, our method explores the model's dynamic behavior from multiple scaled versions of the input and captures the best possible attribution for each input. We demonstrate through extensive experiments that the proposed approach outperforms vanilla and integrated gradients in subjective and quantitative assessment. We also propose a "model perturbation" sanity check to complement the traditionally used "model randomization" test.

Related papers

• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
  We show that the gradient of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
  arXiv  Detail & Related papers  (2023-07-06T15:19:53Z)
• Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization [0.0]
  gradient estimation methods can be used to steer the optimization towards a local optimum. In traffic signal timing optimization problems with high input dimension, the gradient-based methods exhibit substantially superior performance.
  arXiv  Detail & Related papers  (2021-03-23T11:58:21Z)
• Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring [26.434705114982584]
  Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. We introduce a solution to tackle this problem by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN's predictions.
  arXiv  Detail & Related papers  (2021-02-15T19:21:46Z)
• Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods [47.999621481852266]
  Saliency methods interpret the prediction of a neural network by showing the importance of input elements for that prediction. We empirically show that two approaches for handling the gradient information, namely positive aggregation, and positive propagation, break these methods.
  arXiv  Detail & Related papers  (2020-12-01T09:38:54Z)
• A Generalized Stacking for Implementing Ensembles of Gradient Boosting Machines [5.482532589225552]
  An approach for constructing ensembles of gradient boosting models is proposed. It is shown that the proposed approach can be simply extended on arbitrary differentiable combination models.
  arXiv  Detail & Related papers  (2020-10-12T21:05:45Z)
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks [78.76880041670904]
  In neural networks with binary activations and or binary weights the training by gradient descent is complicated. We propose a new method for this estimation problem combining sampling and analytic approximation steps. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models.
  arXiv  Detail & Related papers  (2020-06-04T21:51:21Z)
• 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)
• 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.