Discretized Integrated Gradients for Explaining Language Models

• URL: http://arxiv.org/abs/2108.13654v1
• Date: Tue, 31 Aug 2021 07:36:34 GMT
• Title: Discretized Integrated Gradients for Explaining Language Models
• Authors: Soumya Sanyal, Xiang Ren
• Abstract summary: Integrated Gradients (IG) is a prominent attribution-based explanation algorithm. We propose Discretized Integrated Gradients (DIG) which allows effective attribution along non-linear paths.
• Score: 43.2877233809206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation. It measures feature importance by averaging the model's output gradient interpolated along a straight-line path in the input data space. However, such straight-line interpolated points are not representative of text data due to the inherent discreteness of the word embedding space. This questions the faithfulness of the gradients computed at the interpolated points and consequently, the quality of the generated explanations. Here we propose Discretized Integrated Gradients (DIG), which allows effective attribution along non-linear interpolation paths. We develop two interpolation strategies for the discrete word embedding space that generates interpolation points that lie close to actual words in the embedding space, yielding more faithful gradient computation. We demonstrate the effectiveness of DIG over IG through experimental and human evaluations on multiple sentiment classification datasets. We provide the source code of DIG to encourage reproducible research.

Related papers

• Thinner Latent Spaces: Detecting dimension and imposing invariance through autoencoder gradient constraints [9.380902608139902]
  We show that orthogonality relations within the latent layer of the network can be leveraged to infer the intrinsic dimensionality of nonlinear manifold data sets. We outline the relevant theory relying on differential geometry, and describe the corresponding gradient-descent optimization algorithm.
  arXiv  Detail & Related papers  (2024-08-28T20:56:35Z)
• 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)
• 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)
• Geometrically Guided Integrated Gradients [0.3867363075280543]
  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.
  arXiv  Detail & Related papers  (2022-06-13T05:05:43Z)
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework [14.589372535816619]
  We show how data labeled with semantically continuous attributes can be utilized to conduct a quantitative evaluation of latent-space algorithms. Our framework can be used to complement the standard qualitative comparison, and also enables evaluation for domains (such as graph) in which the visualization is difficult.
  arXiv  Detail & Related papers  (2021-10-13T01:01:42Z)
• Cogradient Descent for Dependable Learning [64.02052988844301]
  We propose a dependable learning based on Cogradient Descent (CoGD) algorithm to address the bilinear optimization problem. CoGD is introduced to solve bilinear problems when one variable is with sparsity constraint. It can also be used to decompose the association of features and weights, which further generalizes our method to better train convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-06-20T04:28:20Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation [67.47159595239798]
  We apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. We achieve comparable performance with advantages in computational and memory overhead.
  arXiv  Detail & Related papers  (2020-03-23T12:28:07Z)

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.