Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation

• URL: http://arxiv.org/abs/2506.11790v2
• Date: Thu, 24 Jul 2025 09:17:21 GMT
• Title: Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
• Authors: Gregor Baer, Isel Grau, Chao Zhang, Pieter Van Gorp,
• Abstract summary: "Class-dependent evaluation effects" raise questions about whether perturbation analysis reliably measures attribution quality.<n>We compare perturbation-based degradation scores with ground truth-based precision-recall metrics using multiple attribution methods.<n>Most critically, we find that perturbation-based and ground truth metrics frequently yield contradictory assessments of attribution quality across classes.
• Score: 5.136283512042341
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating feature attribution methods represents a critical challenge in explainable AI (XAI), as researchers typically rely on perturbation-based metrics when ground truth is unavailable. However, recent work reveals that these evaluation metrics can show different performance across predicted classes within the same dataset. These "class-dependent evaluation effects" raise questions about whether perturbation analysis reliably measures attribution quality, with direct implications for XAI method development and evaluation trustworthiness. We investigate under which conditions these class-dependent effects arise by conducting controlled experiments with synthetic time series data where ground truth feature locations are known. We systematically vary feature types and class contrasts across binary classification tasks, then compare perturbation-based degradation scores with ground truth-based precision-recall metrics using multiple attribution methods. Our experiments demonstrate that class-dependent effects emerge with both evaluation approaches, even in simple scenarios with temporally localized features, triggered by basic variations in feature amplitude or temporal extent between classes. Most critically, we find that perturbation-based and ground truth metrics frequently yield contradictory assessments of attribution quality across classes, with weak correlations between evaluation approaches. These findings suggest that researchers should interpret perturbation-based metrics with care, as they may not always align with whether attributions correctly identify discriminating features. By showing this disconnect, our work points toward reconsidering what attribution evaluation actually measures and developing more rigorous evaluation methods that capture multiple dimensions of attribution quality.

Related papers

• Data Fusion for Partial Identification of Causal Effects [62.56890808004615]
  We propose a novel partial identification framework that enables researchers to answer key questions.<n>Is the causal effect positive or negative? and How severe must assumption violations be to overturn this conclusion?<n>We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance.
  arXiv  Detail & Related papers  (2025-05-30T07:13:01Z)
• Class-Dependent Perturbation Effects in Evaluating Time Series Attributions [5.136283512042341]
  We show previously overlooked class-dependent effects in feature attribution metrics.<n>Our analysis suggests that perturbation-based evaluation may reflect specific model behaviors rather than intrinsic attribution quality.<n>We propose an evaluation framework with a class-aware penalty term to help assess and account for these effects.
  arXiv  Detail & Related papers  (2025-02-24T10:22:03Z)
• Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise [62.997667081978825]
  In high-risk environments, deep learning models need to be able to judge their uncertainty and reject inputs when there is a significant chance of misclassification. We conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise.
  arXiv  Detail & Related papers  (2023-01-03T11:34:36Z)
• A classification performance evaluation measure considering data separability [6.751026374812737]
  We propose a new separability measure--the rate of separability (RS)--based on the data coding rate. We demonstrate the positive correlation between the proposed measure and recognition accuracy in a multi-task scenario constructed from a real dataset.
  arXiv  Detail & Related papers  (2022-11-10T09:18:26Z)
• Systematic Evaluation of Predictive Fairness [60.0947291284978]
  Mitigating bias in training on biased datasets is an important open problem. We examine the performance of various debiasing methods across multiple tasks. We find that data conditions have a strong influence on relative model performance.
  arXiv  Detail & Related papers  (2022-10-17T05:40:13Z)
• Selecting the suitable resampling strategy for imbalanced data classification regarding dataset properties [62.997667081978825]
  In many application domains such as medicine, information retrieval, cybersecurity, social media, etc., datasets used for inducing classification models often have an unequal distribution of the instances of each class. This situation, known as imbalanced data classification, causes low predictive performance for the minority class examples. Oversampling and undersampling techniques are well-known strategies to deal with this problem by balancing the number of examples of each class.
  arXiv  Detail & Related papers  (2021-12-15T18:56:39Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators [91.3755431537592]
  We show that even in arguably the simplest setting, estimation under ignorability assumptions can be misleading. We consider two popular machine learning benchmark datasets for evaluation of heterogeneous treatment effect estimators. We highlight that the inherent characteristics of the benchmark datasets favor some algorithms over others.
  arXiv  Detail & Related papers  (2021-07-28T13:21:27Z)
• Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions [18.351120611713586]
  We develop and rigorously evaluate a deep learning based system that can accurately classify skin conditions. We frame this task as an out-of-distribution (OOD) detection problem. Our novel approach, hierarchical outlier detection (HOD) assigns multiple abstention classes for each training class and jointly performs a coarse classification of inliers vs. outliers.
  arXiv  Detail & Related papers  (2021-04-08T15:15:22Z)
• 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)
• Evaluation metrics for behaviour modeling [2.616915680939834]
  We propose and investigate metrics for evaluating and comparing generative models of behavior learned using imitation learning. These criteria look at longer temporal relationships in behavior, are relevant if behavior has some properties that are inherently unpredictable, and highlight biases in the overall distribution of behaviors produced by the model. We show that the proposed metrics correspond with biologists' intuition about behavior, and allow us to evaluate models, understand their biases, and enable us to propose new research directions.
  arXiv  Detail & Related papers  (2020-07-23T23:47:24Z)

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.