PERFEX: Classifier Performance Explanations for Trustworthy AI Systems

• URL: http://arxiv.org/abs/2212.06045v1
• Date: Mon, 12 Dec 2022 17:03:09 GMT
• Title: PERFEX: Classifier Performance Explanations for Trustworthy AI Systems
• Authors: Erwin Walraven, Ajaya Adhikari, Cor J. Veenman
• Abstract summary: Explanations make predictions actionable to the user. Existing explanation methods, however, typically only provide explanations for individual predictions. This paper presents a method to explain the qualities of a trained base classifier, called PERFormance EXplainer (PERFEX)
• Score: 0.9668407688201357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explainability of a classification model is crucial when deployed in real-world decision support systems. Explanations make predictions actionable to the user and should inform about the capabilities and limitations of the system. Existing explanation methods, however, typically only provide explanations for individual predictions. Information about conditions under which the classifier is able to support the decision maker is not available, while for instance information about when the system is not able to differentiate classes can be very helpful. In the development phase it can support the search for new features or combining models, and in the operational phase it supports decision makers in deciding e.g. not to use the system. This paper presents a method to explain the qualities of a trained base classifier, called PERFormance EXplainer (PERFEX). Our method consists of a meta tree learning algorithm that is able to predict and explain under which conditions the base classifier has a high or low error or any other classification performance metric. We evaluate PERFEX using several classifiers and datasets, including a case study with urban mobility data. It turns out that PERFEX typically has high meta prediction performance even if the base classifier is hardly able to differentiate classes, while giving compact performance explanations.

Related papers

• Prospector Heads: Generalized Feature Attribution for Large Models & Data [82.02696069543454]
  We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods. We demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data.
  arXiv  Detail & Related papers  (2024-02-18T23:01:28Z)
• Bayesian Strategic Classification [11.439576371711711]
  We study the study of partial information release by the learner in strategic classification. We show how such partial information release can, counter-intuitively, benefit the learner's accuracy, despite increasing agents' abilities to manipulate.
  arXiv  Detail & Related papers  (2024-02-13T19:51:49Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
  We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification. XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations. Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
  arXiv  Detail & Related papers  (2023-10-09T08:07:04Z)
• Reconnoitering the class distinguishing abilities of the features, to know them better [6.026640792312181]
  Explainability can allow end-users to have a transparent and humane reckoning of a machine learning scheme's capability and utility. In this work, we explain the features on the basis of their class or category-distinguishing capabilities. We validate the explainability given by our scheme empirically on several real-world, multi-class datasets.
  arXiv  Detail & Related papers  (2022-11-23T08:39:41Z)
• 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)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework [21.055845469999532]
  We propose a learning-from-disagreement framework to visually compare two classification models. Specifically, we train a discriminator to learn from the disagreed instances. We interpret the trained discriminator with the SHAP values of different meta-features.
  arXiv  Detail & Related papers  (2022-01-19T20:15:35Z)
• 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)
• Explainable AI for Classification using Probabilistic Logic Inference [9.656846523452502]
  We present an explainable classification method. Our method works by first constructing a symbolic Knowledge Base from the training data, and then performing probabilistic inferences on such Knowledge Base with linear programming. It identifies decisive features that are responsible for a classification as explanations and produces results similar to the ones found by SHAP, a state of the artley Value based method.
  arXiv  Detail & Related papers  (2020-05-05T11:39:23Z)

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.