A Set Membership Approach to Discovering Feature Relevance and Explaining Neural Classifier Decisions

• URL: http://arxiv.org/abs/2204.02241v2
• Date: Sun, 4 Jun 2023 20:56:01 GMT
• Title: A Set Membership Approach to Discovering Feature Relevance and Explaining Neural Classifier Decisions
• Authors: Stavros P. Adam, Aristidis C. Likas
• Abstract summary: This paper introduces a novel methodology for discovering which features are considered relevant by a trained neural classifier. Although, feature relevance has received much attention in the machine learning literature here we reconsider it in terms of nonlinear parameter estimation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural classifiers are non linear systems providing decisions on the classes of patterns, for a given problem they have learned. The output computed by a classifier for each pattern constitutes an approximation of the output of some unknown function, mapping pattern data to their respective classes. The lack of knowledge of such a function along with the complexity of neural classifiers, especially when these are deep learning architectures, do not permit to obtain information on how specific predictions have been made. Hence, these powerful learning systems are considered as black boxes and in critical applications their use tends to be considered inappropriate. Gaining insight on such a black box operation constitutes a one way approach in interpreting operation of neural classifiers and assessing the validity of their decisions. In this paper we tackle this problem introducing a novel methodology for discovering which features are considered relevant by a trained neural classifier and how they affect the classifier's output, thus obtaining an explanation on its decision. Although, feature relevance has received much attention in the machine learning literature here we reconsider it in terms of nonlinear parameter estimation targeted by a set membership approach which is based on interval analysis. Hence, the proposed methodology builds on sound mathematical approaches and the results obtained constitute a reliable estimation of the classifier's decision premises.

Related papers

• Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices [3.536472734238452]
  We set the task of obtaining an uncertainty estimate for neural networks based on the Transformer architecture. In this paper, we propose a method for uncertainty estimation based on the topological properties of the attention mechanism.
  arXiv  Detail & Related papers  (2023-08-22T09:17:45Z)
• CLIMAX: An exploration of Classifier-Based Contrastive Explanations [5.381004207943597]
  We propose a novel post-hoc model XAI technique that provides contrastive explanations justifying the classification of a black box. Our method, which we refer to as CLIMAX, is based on local classifiers. We show that we achieve better consistency as compared to baselines such as LIME, BayLIME, and SLIME.
  arXiv  Detail & Related papers  (2023-07-02T22:52:58Z)
• Anomaly Detection using Ensemble Classification and Evidence Theory [62.997667081978825]
  We present a novel approach for novel detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We use uncertainty for the anomaly detection approach.
  arXiv  Detail & Related papers  (2022-12-23T00:50:41Z)
• Supervised Feature Compression based on Counterfactual Analysis [3.2458225810390284]
  This work aims to leverage Counterfactual Explanations to detect the important decision boundaries of a pre-trained black-box model. Using the discretized dataset, an optimal Decision Tree can be trained that resembles the black-box model, but that is interpretable and compact.
  arXiv  Detail & Related papers  (2022-11-17T21:16:14Z)
• The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods [86.39044549664189]
  Anomaly detection algorithms for feature-vector data identify anomalies as outliers, but outlier detection has not worked well in deep learning. This paper proposes the Familiarity Hypothesis that these methods succeed because they are detecting the absence of familiar learned features rather than the presence of novelty. The paper concludes with a discussion of whether familiarity detection is an inevitable consequence of representation learning.
  arXiv  Detail & Related papers  (2022-03-04T18:32:58Z)
• 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)
• Neural Networks as Functional Classifiers [0.0]
  We extend notable deep learning methodologies to the domain of functional data for the purpose of classification problems. We highlight the effectiveness of our method in a number of classification applications such as classification of spectrographic data.
  arXiv  Detail & Related papers  (2020-10-09T00:11:01Z)
• Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
  We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition. CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions. Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
  arXiv  Detail & Related papers  (2020-08-12T06:23:49Z)
• Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions [55.660255727031725]
  Influence functions explain the decisions of a model by identifying influential training examples. We conduct a comparison between influence functions and common word-saliency methods on representative tasks. We develop a new measure based on influence functions that can reveal artifacts in training data.
  arXiv  Detail & Related papers  (2020-05-14T00:45:23Z)

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.