Overcoming Common Flaws in the Evaluation of Selective Classification Systems

• URL: http://arxiv.org/abs/2407.01032v2
• Date: Sat, 19 Oct 2024 11:39:46 GMT
• Title: Overcoming Common Flaws in the Evaluation of Selective Classification Systems
• Authors: Jeremias Traub, Till J. Bungert, Carsten T. Lüth, Michael Baumgartner, Klaus H. Maier-Hein, Lena Maier-Hein, Paul F Jaeger,
• Abstract summary: We define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility. We propose the Area under the Generalized Risk Coverage curve ($mathrmAUGRC$), which meets all requirements and can be directly interpreted as the average risk of undetected failures.
• Score: 3.197540295466042
• License:
• Abstract: Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve ($\mathrm{AUGRC}$), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of $\mathrm{AUGRC}$ on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

Related papers

• Trustworthy Classification through Rank-Based Conformal Prediction Sets [9.559062601251464]
  We propose a novel conformal prediction method that employs a rank-based score function suitable for classification models. Our approach constructs prediction sets that achieve the desired coverage rate while managing their size. Our contributions include a novel conformal prediction method, theoretical analysis, and empirical evaluation.
  arXiv  Detail & Related papers  (2024-07-05T10:43:41Z)
• Deep Imbalanced Regression via Hierarchical Classification Adjustment [50.19438850112964]
  Regression tasks in computer vision are often formulated into classification by quantizing the target space into classes. The majority of training samples lie in a head range of target values, while a minority of samples span a usually larger tail range. We propose to construct hierarchical classifiers for solving imbalanced regression tasks. Our novel hierarchical classification adjustment (HCA) for imbalanced regression shows superior results on three diverse tasks.
  arXiv  Detail & Related papers  (2023-10-26T04:54:39Z)
• Probabilistic Safety Regions Via Finite Families of Scalable Classifiers [2.431537995108158]
  Supervised classification recognizes patterns in the data to separate classes of behaviours. Canonical solutions contain misclassification errors that are intrinsic to the numerical approximating nature of machine learning. We introduce the concept of probabilistic safety region to describe a subset of the input space in which the number of misclassified instances is probabilistically controlled.
  arXiv  Detail & Related papers  (2023-09-08T22:40:19Z)
• A Universal Unbiased Method for Classification from Aggregate Observations [115.20235020903992]
  This paper presents a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary losses. Our proposed method not only guarantees the risk consistency due to the unbiased risk estimator but also can be compatible with arbitrary losses.
  arXiv  Detail & Related papers  (2023-06-20T07:22:01Z)
• A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification [0.491574468325115]
  We present a large-scale empirical study for the first time enabling benchmarking confidence scoring functions. The revelation of a simple softmax response baseline as the overall best performing method underlines the drastic shortcomings of current evaluation.
  arXiv  Detail & Related papers  (2022-11-28T12:25:27Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)
• Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification [94.55805516167369]
  We propose a new approach for binary classification from m U-sets for $mge2$. Our key idea is to consider an auxiliary classification task called surrogate set classification (SSC)
  arXiv  Detail & Related papers  (2021-02-01T07:36:38Z)
• Distribution-Free, Risk-Controlling Prediction Sets [112.9186453405701]
  We show how to generate set-valued predictions from a black-box predictor that control the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any dataset by using a holdout set to calibrate the size of the prediction sets.
  arXiv  Detail & Related papers  (2021-01-07T18:59:33Z)
• A Skew-Sensitive Evaluation Framework for Imbalanced Data Classification [11.125446871030734]
  Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes. We propose a simple and general-purpose evaluation framework for imbalanced data classification that is sensitive to arbitrary skews in class cardinalities and importances.
  arXiv  Detail & Related papers  (2020-10-12T19:47:09Z)
• Classifier uncertainty: evidence, potential impact, and probabilistic treatment [0.0]
  We present an approach to quantify the uncertainty of classification performance metrics based on a probability model of the confusion matrix. We show that uncertainties can be surprisingly large and limit performance evaluation.
  arXiv  Detail & Related papers  (2020-06-19T12:49:19Z)

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.