特征污染：神经网络学习不相关特征并无法泛化
Feature contamination: Neural networks learn uncorrelated features and fail to generalize
AI总结：
本研究揭示深度神经网络分布外泛化的根本困难，实证表明拟合泛化教师网络表示不足以让学生网络泛化，通过理论分析发现“特征污染”机制，为非线性特征学习动态提供新见解并强调归纳偏置的必要性。
摘要：
学习在分布偏移下可泛化的表示对于构建鲁棒的机器学习模型至关重要。然而，尽管近年来付出了巨大努力，该方向的算法进展仍然有限。在这项工作中，我们试图理解深度神经网络分布外泛化的根本困难。首先，我们通过实证研究表明，一个或许令人惊讶的现象：即使允许神经网络显式拟合能够分布外泛化的教师网络的表示，也不足以让学生网络实现泛化。然后，通过对结构化特征模型下由随机梯度下降（SGD）优化的两层ReLU网络的理论研究，我们发现了神经网络一个根本且未被探索的特征学习倾向——特征污染：神经网络会将不相关特征与预测性特征一同学习，导致分布偏移下的泛化失败。值得注意的是，这一机制与文献中普遍将泛化失败归因于虚假相关性的叙事存在本质区别。总体而言，我们的结果为神经网络的非线性特征学习动态提供了新见解，并强调了在分布外泛化中考虑归纳偏置的必要性。
英文摘要：
Learning representations that generalize under distribution shifts is critical for building robust machine learning models. However, despite significant efforts in recent years, algorithmic advances in this direction have been limited. In this work, we seek to understand the fundamental difficulty of out-of-distribution generalization with deep neural networks. We first empirically show that perhaps surprisingly, even allowing a neural network to explicitly fit the representations obtained from a teacher network that can generalize out-of-distribution is insufficient for the generalization of the student network. Then, by a theoretical study of two-layer ReLU networks optimized by stochastic gradient descent (SGD) under a structured feature model, we identify a fundamental yet unexplored feature learning proclivity of neural networks, feature contamination: neural networks can learn uncorrelated features together with predictive features, resulting in generalization failure under distribution shifts. Notably, this mechanism essentially differs from the prevailing narrative in the literature that attributes the generalization failure to spurious correlations. Overall, our results offer new insights into the non-linear feature learning dynamics of neural networks and highlight the necessity of considering inductive biases in out-of-distribution generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
