Hide&Seek: Learning to Explain in an End-to-End Differentiable Network

• URL: http://arxiv.org/abs/2608.16689v1
• Date: Mon, 17 Aug 2026 15:10:05 GMT
• Title: Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
• Abstract summary: We present Hide&Seek, an end-to-end differentiable model for instance-wise feature selection.<n>We jointly learn feature selection and prediction under a single objective without information leakage.<n>We achieve this by reformulating feature removal as a differentiable operation where instead of discretely removing features, we replace a proportion of each feature.
• Score: 3.2880869992413246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instance-wise feature selection is a valuable tool for interpreting labeled data and the predictions of black-box models. In contrast to global feature selection techniques, instance-wise methods dynamically identify important features for each instance. A growing number of methods learn a selector, which identifies important features, and a predictor, which uses these to make predictions. However, these pioneering methods face challenges including information leakage and lack of differentiability, which can slow training. In this paper, we present Hide&Seek, an end-to-end differentiable model for instance-wise feature selection. We jointly learn feature selection and prediction under a single objective without information leakage. Hide&Seek outperforms existing state-of-the-art models across a range of experiments and is fast to train. We achieve this by reformulating feature removal as a differentiable operation where instead of discretely removing features, we replace a proportion of each feature. Training is further stabilized via a parsimony-weight annealing framework.

Related papers

• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• Don't Forget Too Much: Towards Machine Unlearning on Feature Level [16.32116782528703]
  We propose a refined granularity unlearning scheme referred to as feature unlearning" We first explore two scenarios based on whether the annotation information about the features is given. We propose an adversarial learning approach to automatically remove effects about features.
  arXiv  Detail & Related papers  (2024-06-16T14:08:46Z)
• 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)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• Ensembling improves stability and power of feature selection for deep learning models [11.973624420202388]
  In this paper, we show that inherentity in the design and training of deep learning models makes commonly used feature importance scores unstable. We explore the ensembling of feature importance scores of models across different epochs and find that this simple approach can substantially address this issue. We present a framework to combine the feature importance of trained models and instead of selecting features from one best model, we perform an ensemble of feature importance scores from numerous good models.
  arXiv  Detail & Related papers  (2022-10-02T19:07:53Z)
• Deep Feature Selection Using a Novel Complementary Feature Mask [5.904240881373805]
  We deal with feature selection by exploiting the features with less importance scores. We propose a feature selection framework based on a novel complementary feature mask. Our method is generic and can be easily integrated into existing deep-learning-based feature selection approaches.
  arXiv  Detail & Related papers  (2022-09-25T18:03:30Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Dynamic Instance-Wise Classification in Correlated Feature Spaces [15.351282873821935]
  In a typical machine learning setting, the predictions on all test instances are based on a common subset of features discovered during model training. A new method is proposed that sequentially selects the best feature to evaluate for each test instance individually, and stops the selection process to make a prediction once it determines that no further improvement can be achieved with respect to classification accuracy. The effectiveness, generalizability, and scalability of the proposed method is illustrated on a variety of real-world datasets from diverse application domains.
  arXiv  Detail & Related papers  (2021-06-08T20:20:36Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.