提出可端到端训练的实例级特征选择模型，提升解释性与训练效率。
Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
- 将特征剔除转化为可微操作，用替换代替离散删除
- 在多个数据集上超越现有最佳模型，训练速度更快
- 适合需要高解释性的机器学习应用
实例级特征选择是解释标注数据和黑箱模型预测的重要工具。与全局特征选择不同，实例级方法能为每个样本动态识别重要特征。当前多数方法通过学习一个选择器和一个预测器来实现，但存在信息泄露和不可微等问题，影响训练效率。本文提出Hide&Seek，一种端到端可微的实例级特征选择模型，在单一目标下联合学习特征选择与预测，避免信息泄露。通过将特征移除重构为可微操作（用部分特征值替换），并引入稀疏性权重渐进调节机制，显著稳定训练过程。实验表明，Hide&Seek在多个基准数据集上均优于现有最先进模型，且训练速度快。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。