Class-Dependent Perturbation Effects in Evaluating Time Series Attributions

• URL: http://arxiv.org/abs/2502.17022v2
• Date: Tue, 01 Apr 2025 13:19:41 GMT
• Title: Class-Dependent Perturbation Effects in Evaluating Time Series Attributions
• Authors: Gregor Baer, Isel Grau, Chao Zhang, Pieter Van Gorp,
• Abstract summary: 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.
• Score: 5.136283512042341
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution methods aim to identify which input features contribute the most to a model's prediction, with their evaluation typically relying on perturbation-based metrics. Through systematic empirical analysis across multiple datasets, model architectures, and perturbation strategies, we reveal previously overlooked class-dependent effects in these metrics: they show varying effectiveness across classes, achieving strong results for some while remaining less sensitive to others. In particular, we find that the most effective perturbation strategies often demonstrate the most pronounced class differences. Our analysis suggests that these effects arise from the learned biases of classifiers, indicating that perturbation-based evaluation may reflect specific model behaviors rather than intrinsic attribution quality. We propose an evaluation framework with a class-aware penalty term to help assess and account for these effects in evaluating feature attributions, offering particular value for class-imbalanced datasets. Although our analysis focuses on time series classification, these class-dependent effects likely extend to other structured data domains where perturbation-based evaluation is common.

Related papers

• On the importance of structural identifiability for machine learning with partially observed dynamical systems [0.7864304771129751]
  We use structural identifiability analysis to explicitly relate parameter configurations that are associated with identical system outputs.<n>Our results demonstrate the importance of accounting for structural identifiability, a topic that has received relatively little attention from the machine learning community.
  arXiv  Detail & Related papers  (2025-02-06T15:06:52Z)
• Understanding the Detrimental Class-level Effects of Data Augmentation [63.1733767714073]
  achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. We present a framework for understanding how DA interacts with class-level learning dynamics. We show that simple class-conditional augmentation strategies improve performance on the negatively affected classes.
  arXiv  Detail & Related papers  (2023-12-07T18:37:43Z)
• Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study [71.84852429039881]
  Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise. We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
  arXiv  Detail & Related papers  (2023-06-13T12:43:59Z)
• Data-Driven Estimation of Heterogeneous Treatment Effects [15.140272661540655]
  Estimating how a treatment affects different individuals, known as heterogeneous treatment effect estimation, is an important problem in empirical sciences. We provide a survey of state-of-the-art data-driven methods for heterogeneous treatment effect estimation using machine learning.
  arXiv  Detail & Related papers  (2023-01-16T21:36:49Z)
• 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)
• An evaluation framework for comparing causal inference models [3.1372269816123994]
  We use the proposed evaluation methodology to compare several state-of-the-art causal effect estimation models. The main motivation behind this approach is the elimination of the influence of a small number of instances or simulation on the benchmarking process.
  arXiv  Detail & Related papers  (2022-08-31T21:04:20Z)
• 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)
• Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification [75.49600684537117]
  Data management research is showing an increasing presence and interest in topics related to data and algorithmic fairness. We contribute a broad analysis of 13 fair classification approaches and additional variants, over their correctness, fairness, efficiency, scalability, and stability. Our analysis highlights novel insights on the impact of different metrics and high-level approach characteristics on different aspects of performance.
  arXiv  Detail & Related papers  (2021-01-18T22:55:40Z)
• 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)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)

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.