Leveraging Sparse Linear Layers for Debuggable Deep Networks

• URL: http://arxiv.org/abs/2105.04857v1
• Date: Tue, 11 May 2021 08:15:25 GMT
• Title: Leveraging Sparse Linear Layers for Debuggable Deep Networks
• Authors: Eric Wong, Shibani Santurkar, Aleksander M\k{a}dry
• Abstract summary: We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
• Score: 86.94586860037049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantiatively via numerical and human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks. The code for our toolkit can be found at https://github.com/madrylab/debuggabledeepnetworks.

Related papers

• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Seeing in Words: Learning to Classify through Language Bottlenecks [59.97827889540685]
  Humans can explain their predictions using succinct and intuitive descriptions. We show that a vision model whose feature representations are text can effectively classify ImageNet images.
  arXiv  Detail & Related papers  (2023-06-29T00:24:42Z)
• Learning sparse features can lead to overfitting in neural networks [9.2104922520782]
  We show that feature learning can perform worse than lazy training. Although sparsity is known to be essential for learning anisotropic data, it is detrimental when the target function is constant or smooth.
  arXiv  Detail & Related papers  (2022-06-24T14:26:33Z)
• Contrasting random and learned features in deep Bayesian linear regression [12.234742322758418]
  We study how the ability to learn affects the generalization performance of a simple class of models. By comparing deep random feature models to deep networks in which all layers are trained, we provide a detailed characterization of the interplay between width, depth, data density, and prior mismatch.
  arXiv  Detail & Related papers  (2022-03-01T15:51:29Z)
• A Light-weight Interpretable CompositionalNetwork for Nuclei Detection and Weakly-supervised Segmentation [10.196621315018884]
  Deep neural networks usually require large numbers of annotated data to train vast parameters. We propose to build a data-efficient model, which only requires partial annotation, specifically on isolated nucleus.
  arXiv  Detail & Related papers  (2021-10-26T16:44:08Z)
• Dive into Layers: Neural Network Capacity Bounding using Algebraic Geometry [55.57953219617467]
  We show that the learnability of a neural network is directly related to its size. We use Betti numbers to measure the topological geometric complexity of input data and the neural network. We perform the experiments on a real-world dataset MNIST and the results verify our analysis and conclusion.
  arXiv  Detail & Related papers  (2021-09-03T11:45:51Z)
• Locally Sparse Networks for Interpretable Predictions [7.362415721170984]
  We propose a framework for training locally sparse neural networks where the local sparsity is learned via a sample-specific gating mechanism. The sample-specific sparsity is predicted via a textitgating network, which is trained in tandem with the textitprediction network. We demonstrate that our method outperforms state-of-the-art models when predicting the target function with far fewer features per instance.
  arXiv  Detail & Related papers  (2021-06-11T15:46:50Z)
• An Introduction to Robust Graph Convolutional Networks [71.68610791161355]
  We propose a novel Robust Graph Convolutional Neural Networks for possible erroneous single-view or multi-view data. By incorporating an extra layers via Autoencoders into traditional graph convolutional networks, we characterize and handle typical error models explicitly.
  arXiv  Detail & Related papers  (2021-03-27T04:47:59Z)
• The Connection Between Approximation, Depth Separation and Learnability in Neural Networks [70.55686685872008]
  We study the connection between learnability and approximation capacity. We show that learnability with deep networks of a target function depends on the ability of simpler classes to approximate the target.
  arXiv  Detail & Related papers  (2021-01-31T11:32:30Z)
• Learning Parities with Neural Networks [45.6877715768796]
  We make a step towards showing leanability of models that are inherently non-linear. We show that under certain distributions, sparse parities are learnable via gradient decent on depth-two network.
  arXiv  Detail & Related papers  (2020-02-18T06:44:17Z)

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.