A Neurosymbolic Framework for Bias Correction in Convolutional Neural Networks

• URL: http://arxiv.org/abs/2405.15886v4
• Date: Thu, 22 Aug 2024 23:10:20 GMT
• Title: A Neurosymbolic Framework for Bias Correction in Convolutional Neural Networks
• Authors: Parth Padalkar, Natalia Ślusarz, Ekaterina Komendantskaya, Gopal Gupta,
• Abstract summary: We introduce a neurosymbolic framework called NeSyBiCor for bias correction in a trained CNN. We show that our framework successfully corrects the biases of CNNs trained with subsets of classes from the "Places" dataset.
• Score: 2.249916681499244
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent efforts in interpreting Convolutional Neural Networks (CNNs) focus on translating the activation of CNN filters into a stratified Answer Set Program (ASP) rule-sets. The CNN filters are known to capture high-level image concepts, thus the predicates in the rule-set are mapped to the concept that their corresponding filter represents. Hence, the rule-set exemplifies the decision-making process of the CNN w.r.t the concepts that it learns for any image classification task. These rule-sets help understand the biases in CNNs, although correcting the biases remains a challenge. We introduce a neurosymbolic framework called NeSyBiCor for bias correction in a trained CNN. Given symbolic concepts, as ASP constraints, that the CNN is biased towards, we convert the concepts to their corresponding vector representations. Then, the CNN is retrained using our novel semantic similarity loss that pushes the filters away from (or towards) learning the desired/undesired concepts. The final ASP rule-set obtained after retraining, satisfies the constraints to a high degree, thus showing the revision in the knowledge of the CNN. We demonstrate that our NeSyBiCor framework successfully corrects the biases of CNNs trained with subsets of classes from the "Places" dataset while sacrificing minimal accuracy and improving interpretability.

Related papers

• Demystifying CNNs for Images by Matched Filters [13.121514086503591]
  convolution neural networks (CNN) have been revolutionising the way we approach and use intelligent machines in the Big Data era. CNNs have been put under scrutiny owing to their textitblack-box nature, as well as the lack of theoretical support and physical meanings of their operation. This paper attempts to demystify the operation of CNNs by employing the perspective of matched filtering.
  arXiv  Detail & Related papers  (2022-10-16T12:39:17Z)
• CNNs Avoid Curse of Dimensionality by Learning on Patches [11.546219454021935]
  We argue that convolutional neural networks (CNNs) operate on the domain of image patches. Our work is the first to derive an a priori error bound for the generalization error of CNNs. Our patch-based theory also offers explanation for why data augmentation techniques like Cutout, CutMix and random cropping are effective in improving the generalization error of CNNs.
  arXiv  Detail & Related papers  (2022-05-22T06:22:27Z)
• Deeply Explain CNN via Hierarchical Decomposition [75.01251659472584]
  In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect the network prediction. This paper introduces a hierarchical decomposition framework to explain CNN's decision-making process in a top-down manner.
  arXiv  Detail & Related papers  (2022-01-23T07:56:04Z)
• Interpretable Compositional Convolutional Neural Networks [20.726080433723922]
  We propose a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN. In a compositional CNN, each filter is supposed to consistently represent a specific compositional object part or image region with a clear meaning. Our method can be broadly applied to different types of CNNs.
  arXiv  Detail & Related papers  (2021-07-09T15:01:24Z)
• BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks [65.2021953284622]
  We study robustness of CNNs against white-box and black-box adversarial attacks. Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
  arXiv  Detail & Related papers  (2021-03-14T20:43:19Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications [2.1485350418225244]
  We propose using the feature space that results from the training dataset to automatically label problematic images. The resulting semi-supervised incremental learning process allows improving the classification accuracy of new instances by 40%.
  arXiv  Detail & Related papers  (2020-11-11T12:31:48Z)
• SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate [51.67813146731196]
  Convolutional neural networks (CNN) have emerged as a powerful tool for solving computational imaging reconstruction problems. CNNs are difficult-to-understand black-boxes. This limitation is a major barrier to their use in safety-critical applications like medical imaging.
  arXiv  Detail & Related papers  (2020-10-25T20:29:41Z)
• Shape Defense Against Adversarial Attacks [47.64219291655723]
  Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. Here, we explore how shape bias can be incorporated into CNNs to improve their robustness. Two algorithms are proposed, based on the observation that edges are invariant to moderate imperceptible perturbations.
  arXiv  Detail & Related papers  (2020-08-31T03:23:59Z)
• Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification [3.0204693431381515]
  We adjust the architecture of the tiled convolutional neural network (tiled CNN) to improve its extraction of salient features for sentiment analysis. Knowing that the major drawback of the tiled CNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled CNN. Experiments on the datasets of IMDB movie reviews and SemEval 2017 demonstrate the efficiency of the hybrid tiled CNN.
  arXiv  Detail & Related papers  (2020-01-31T14:08:15Z)
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks [52.972605601174955]
  We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes. We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
  arXiv  Detail & Related papers  (2019-03-24T19:42:39Z)

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.