Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals

• URL: http://arxiv.org/abs/2406.05477v1
• Date: Sat, 8 Jun 2024 13:52:02 GMT
• Title: Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
• Authors: Susu Sun, Stefano Woerner, Andreas Maier, Lisa M. Koch, Christian F. Baumgartner,
• Abstract summary: Interpretability is crucial for machine learning algorithms in high-stakes medical applications. Attri-Net is an inherently interpretable model for multi-label classification that provides local and global explanations.
• Score: 4.384272169863716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions. Post-hoc explanation methods provide a way to understand neural networks but have been shown to suffer from conceptual problems. Moreover, current research largely focuses on providing local explanations for individual samples rather than global explanations for the model itself. In this paper, we propose Attri-Net, an inherently interpretable model for multi-label classification that provides local and global explanations. Attri-Net first counterfactually generates class-specific attribution maps to highlight the disease evidence, then performs classification with logistic regression classifiers based solely on the attribution maps. Local explanations for each prediction can be obtained by interpreting the attribution maps weighted by the classifiers' weights. Global explanation of whole model can be obtained by jointly considering learned average representations of the attribution maps for each class (called the class centers) and the weights of the linear classifiers. To ensure the model is ``right for the right reason", we further introduce a mechanism to guide the model's explanations to align with human knowledge. Our comprehensive evaluations show that Attri-Net can generate high-quality explanations consistent with clinical knowledge while not sacrificing classification performance.

Related papers

• Simple and Interpretable Probabilistic Classifiers for Knowledge Graphs [0.0]
  We describe an inductive approach based on learning simple belief networks. We show how such models can be converted into (probabilistic) axioms (or rules)
  arXiv  Detail & Related papers  (2024-07-09T17:05:52Z)
• Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals [9.485195366036292]
  Interpretability is essential for machine learning algorithms in high-stakes application fields such as medical image analysis. We propose Attri-Net, an inherently interpretable model for multi-label classification. We find that Attri-Net produces high-quality multi-label explanations consistent with clinical knowledge.
  arXiv  Detail & Related papers  (2023-03-01T13:32:55Z)
• A Top-down Supervised Learning Approach to Hierarchical Multi-label Classification in Networks [0.21485350418225244]
  This paper presents a general prediction model to hierarchical multi-label classification (HMC), where the attributes to be inferred can be specified as a strict poset. It is based on a top-down classification approach that addresses hierarchical multi-label classification with supervised learning by building a local classifier per class. The proposed model is showcased with a case study on the prediction of gene functions for Oryza sativa Japonica, a variety of rice.
  arXiv  Detail & Related papers  (2022-03-23T17:29:17Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• Information-theoretic Evolution of Model Agnostic Global Explanations [10.921146104622972]
  We present a novel model-agnostic approach that derives rules to globally explain the behavior of classification models trained on numerical and/or categorical data. Our approach has been deployed in a leading digital marketing suite of products.
  arXiv  Detail & Related papers  (2021-05-14T16:52:16Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)
• Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia [7.372797734096181]
  Trust in predictions made by machine learning models is increased if the model generalizes well on previously unseen samples. We propose a method that enhances the explainability of image classifications through better localization by mitigating the model uncertainty induced by class overlap. Our method is particularly promising in real-world class overlap scenarios, such as COVID-19 and pneumonia, where expertly labeled data for localization is not readily available.
  arXiv  Detail & Related papers  (2020-08-06T20:47:36Z)

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.