Tangentially Aligned Integrated Gradients for User-Friendly Explanations

• URL: http://arxiv.org/abs/2503.08240v1
• Date: Tue, 11 Mar 2025 10:04:13 GMT
• Title: Tangentially Aligned Integrated Gradients for User-Friendly Explanations
• Authors: Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew,
• Abstract summary: Integrated gradients are prevalent in machine learning to address the black-box problem of neural networks.<n>The choice of base-point is not a priori obvious and can lead to drastically different explanations.<n>We propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation.
• Score: 5.286919475372417
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious and can lead to drastically different explanations. There is a longstanding hypothesis that data lies on a low dimensional Riemannian manifold. The quality of explanations on a manifold can be measured by the extent to which an explanation for a point lies in its tangent space. In this work, we propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation. We formalise the notion of tangential alignment and provide theoretical conditions under which a base-point choice will provide explanations lying in the tangent space. We demonstrate how to approximate the optimal base-point on several well-known image classification datasets. Furthermore, we compare the optimal base-point choice with common base-points and three gradient explainability models.

Related papers

• Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness [51.302674884611335]
  This work introduces a hybrid non-Euclidean optimization method which generalizes norm clipping by combining steepest descent and conditional gradient approaches.<n>We discuss how to instantiate the algorithms for deep learning and demonstrate their properties on image classification and language modeling.
  arXiv  Detail & Related papers  (2025-06-02T17:34:29Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• 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)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation [73.77505964222632]
  We present a learning-based method, namely GeoUDF, to tackle the problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation. To extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module.
  arXiv  Detail & Related papers  (2022-11-30T06:02:01Z)
• The Manifold Hypothesis for Gradient-Based Explanations [55.01671263121624]
  gradient-based explanation algorithms provide perceptually-aligned explanations. We show that the more a feature attribution is aligned with the tangent space of the data, the more perceptually-aligned it tends to be. We suggest that explanation algorithms should actively strive to align their explanations with the data manifold.
  arXiv  Detail & Related papers  (2022-06-15T08:49:24Z)
• Maximum Entropy Baseline for Integrated Gradients [0.0]
  Integrated Gradients (IG) is one of the most popular explainability methods available. This study proposes a new uniform baseline, i.e., the Maximum Entropy Baseline.
  arXiv  Detail & Related papers  (2022-04-12T17:04:42Z)
• Identifying the latent space geometry of network models through analysis of curvature [7.644165047073435]
  We present a method to consistently estimate the manifold type, dimension, and curvature from an empirically relevant class of latent spaces. Our core insight comes by representing the graph as a noisy distance matrix based on the ties between cliques.
  arXiv  Detail & Related papers  (2020-12-19T00:35:29Z)
• Deep Magnification-Flexible Upsampling over 3D Point Clouds [103.09504572409449]
  We propose a novel end-to-end learning-based framework to generate dense point clouds. We first formulate the problem explicitly, which boils down to determining the weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted weights as well as the high-order refinements.
  arXiv  Detail & Related papers  (2020-11-25T14:00:18Z)
• A Baseline for Shapley Values in MLPs: from Missingness to Neutrality [3.5939555573102853]
  Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. In this paper, we present a method for choosing a baseline according to a neutrality value. We empirically validate our choice of baseline in the context of binary classification tasks.
  arXiv  Detail & Related papers  (2020-06-08T19:29:36Z)
• Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization [15.2292571922932]
  We propose an approach to answering this question based on a hypothesis about the dynamics of gradient descent. We show that changes to the network parameters during training are biased towards those that (locally) simultaneously benefit many examples.
  arXiv  Detail & Related papers  (2020-02-25T03:59:31Z)

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.