XtrAIn: Training-Guided Occlusion for Feature Attribution

• URL: http://arxiv.org/abs/2606.10877v1
• Date: Tue, 09 Jun 2026 13:52:05 GMT
• Title: XtrAIn: Training-Guided Occlusion for Feature Attribution
• Abstract summary: Occlusion-based attribution methods can estimate feature importance by perturbing input features and measuring the resulting change in model output.<n>We introduce XtrAIn, a training-guided attribution method that transfers the occlusion operation from the input space to the parameter space.<n>XtrAIn produces cleaner and more interpretable attribution patterns than standard attribution baselines.
• Score: 3.3609128464006015
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output. However, their reliability is strongly affected by how feature removal is implemented: externally selected baselines can introduce bias, out-of-distribution samples, and unstable explanations, while in nonlinear models the occlusion of a set of features can also alter the contribution of non-occluded features. We refer to this effect as attribution shift, as the attribution scores of the non-occluded features drift from their initial values. To challenge these major issues that render explanations unstable, we introduce XtrAIn, a training-guided attribution method that transfers the occlusion operation from the input space to the parameter space. Instead of replacing input values with hand-crafted baselines, XtrAIn follows the model's training trajectory and measures how feature-associated parameter updates affect the output logits. We further introduce Xstep, a lightweight approximation for reducing computational cost, and XtrAIn+, a target-focused variant that emphasizes updates aligned with the target class. Experiments on controlled image datasets and PAM50 breast-cancer subtype classification show that the proposed methods produce cleaner and more interpretable attribution patterns than standard attribution baselines. Overall, XtrAIn provides a training-aware perspective on feature attribution and offers a useful diagnostic tool for studying how feature-level evidence is formed during training.

Related papers

• Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution [29.066960285647962]
  Integrated Diffusion Gradients (DiffIG) is a novel method that reformulates path generation as a conditional generative modeling problem.<n>We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations.<n>This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.
  arXiv  Detail & Related papers  (2026-06-21T03:04:35Z)
• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations [25.503211313768062]
  We propose a bilevel meta-learning method that performs augmentation directly in feature space to improve spurious correlation handling in the classifier head.<n>By operating at the backbone output rather than in pixel space, the method is highly efficient and stable, requiring only a few minutes of training on a single GPU.
  arXiv  Detail & Related papers  (2026-03-31T06:32:56Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Distributional Training Data Attribution: What do Influence Functions Sample? [25.257922996567178]
  We introduce distributional training data attribution (d-TDA)<n>The goal of d-TDA is to predict how the distribution of model outputs depends upon the dataset.<n>We find that influence functions (IFs) are'secretly distributional'
  arXiv  Detail & Related papers  (2025-06-15T21:02:36Z)
• Influence Functions for Scalable Data Attribution in Diffusion Models [52.92223039302037]
  Diffusion models have led to significant advancements in generative modelling.<n>Yet their widespread adoption poses challenges regarding data attribution and interpretability.<n>We develop an influence functions framework to address these challenges.
  arXiv  Detail & Related papers  (2024-10-17T17:59:02Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Explainability of Machine Learning Models under Missing Data [3.0485328005356136]
  Missing data is a prevalent issue that can significantly impair model performance and explainability.<n>This paper briefly summarizes the development of the field of missing data and investigates the effects of various imputation methods on SHAP.
  arXiv  Detail & Related papers  (2024-06-29T11:31:09Z)
• Data augmentation and explainability for bias discovery and mitigation in deep learning [0.0]
  This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data and models, with a particular focus on bias in machine learning pipelines. The next chapter outlines a taxonomy and methods of Explainable AI as a way to justify predictions and control and improve the model.
  arXiv  Detail & Related papers  (2023-08-18T11:02:27Z)
• Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
  We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
  arXiv  Detail & Related papers  (2022-01-28T22:03:50Z)

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.