Model Guidance via Robust Feature Attribution

• URL: http://arxiv.org/abs/2506.19680v1
• Date: Tue, 24 Jun 2025 14:47:15 GMT
• Title: Model Guidance via Robust Feature Attribution
• Authors: Mihnea Ghitu, Matthew Wicker, Vihari Piratla,
• Abstract summary: We show that our approach consistently reduces test-time misclassifications by 20% compared to state-of-the-art methods.<n>We also extend prior experimental settings to include natural language processing tasks.
• Score: 11.68718298442961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical imaging and natural language processing, where it may lead to real-world harms. A common mitigation strategy leverages annotations (provided by humans or machines) indicating which features are relevant or irrelevant. These annotations are compared to model explanations, typically in the form of feature salience, and used to guide the loss function during training. Unfortunately, recent works have demonstrated that feature salience methods are unreliable and therefore offer a poor signal to optimize. In this work, we propose a simplified objective that simultaneously optimizes for explanation robustness and mitigation of shortcut learning. Unlike prior objectives with similar aims, we demonstrate theoretically why our approach ought to be more effective. Across a comprehensive series of experiments, we show that our approach consistently reduces test-time misclassifications by 20% compared to state-of-the-art methods. We also extend prior experimental settings to include natural language processing tasks. Additionally, we conduct novel ablations that yield practical insights, including the relative importance of annotation quality over quantity. Code for our method and experiments is available at: https://github.com/Mihneaghitu/ModelGuidanceViaRobustFeatureAttribution.

Related papers

• DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models [50.54264918467997]
  Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks.<n>Recent research has revealed that these models often rely on superficial features and shortcuts instead of developing a genuine understanding of language.<n>We propose Divergence Based Regularization (DBR) to mitigate this shortcut learning behavior.
  arXiv  Detail & Related papers  (2025-02-25T16:44:10Z)
• Post-hoc Spurious Correlation Neutralization with Single-Weight Fictitious Class Unlearning [46.2410852276839]
  Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss.<n>Some of these features might be spuriously correlated with the target labels, leading to incorrect predictions by the model.<n>We propose a unique precise class removal technique that employs a single-weight modification.
  arXiv  Detail & Related papers  (2025-01-24T02:22:42Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• An Information Theoretic Approach to Machine Unlearning [43.423418819707784]
  To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important.<n>In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten.<n>We derive a simple but principled zero-shot unlearning method based on the geometry of the model.
  arXiv  Detail & Related papers  (2024-02-02T13:33:30Z)
• Localized Shortcut Removal [4.511561231517167]
  High performance on held-out test data does not necessarily indicate that a model generalizes or learns anything meaningful. This is often due to the existence of machine learning shortcuts - features in the data that are predictive but unrelated to the problem at hand. We use an adversarially trained lens to detect and eliminate highly predictive but semantically unconnected clues in images.
  arXiv  Detail & Related papers  (2022-11-24T13:05:33Z)
• Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future [63.99570204416711]
  We reimplement 18 methods for detecting potential annotation errors and evaluate them on 9 English datasets. We define a uniform evaluation setup including a new formalization of the annotation error detection task. We release our datasets and implementations in an easy-to-use and open source software package.
  arXiv  Detail & Related papers  (2022-06-05T22:31:45Z)
• Finding Significant Features for Few-Shot Learning using Dimensionality Reduction [0.0]
  This module helps to improve the accuracy performance by allowing the similarity function, given by the metric learning method, to have more discriminative features for the classification. Our method outperforms the metric learning baselines in the miniImageNet dataset by around 2% in accuracy performance.
  arXiv  Detail & Related papers  (2021-07-06T16:36:57Z)
• Can contrastive learning avoid shortcut solutions? [88.249082564465]
  implicit feature modification (IFM) is a method for altering positive and negative samples in order to guide contrastive models towards capturing a wider variety of predictive features. IFM reduces feature suppression, and as a result improves performance on vision and medical imaging tasks.
  arXiv  Detail & Related papers  (2021-06-21T16:22:43Z)
• Representation Learning for Weakly Supervised Relation Extraction [19.689433249830465]
  In this thesis, we present several novel unsupervised pre-training models to learn the distributed text representation features. The experiments have demonstrated that this type of feature, combine with the traditional hand-crafted features, could improve the performance of the logistic classification model for relation extraction.
  arXiv  Detail & Related papers  (2021-04-10T12:22:25Z)
• Confident Coreset for Active Learning in Medical Image Analysis [57.436224561482966]
  We propose a novel active learning method, confident coreset, which considers both uncertainty and distribution for effectively selecting informative samples. By comparative experiments on two medical image analysis tasks, we show that our method outperforms other active learning methods.
  arXiv  Detail & Related papers  (2020-04-05T13:46:16Z)

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.