元学习不学习：在干扰变量变化族下稳健地指导元学习
Meta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Families
AI总结：
针对神经网络依赖伪特征导致泛化困难的问题，提出RIME方法，通过同时整合正负归纳偏置，在干扰变量变化族的知情元学习场景下实现了分布鲁棒的最先进性能。
摘要：
在伪预测因子和因果预测因子同时存在的场景中，以经验风险最小化（ERM）为目标训练且无额外归纳偏置的标准神经网络，往往依赖于伪特征。因此，必须引入额外的归纳偏置以引导网络走向可泛化的假设。这些伪特征通常在相关任务间共享，例如根据来自不同医院的图像扫描估计疾病预后，这使得泛化挑战更加严峻。在此类场景中，方法能够整合适当的归纳偏置以在干扰变量变化族和任务族间实现泛化至关重要。受此场景启发，我们提出了RIME（Robustly Informed Meta lEarning），这是一种在正负归纳偏置（即学习什么和不学习什么）同时存在的情况下进行元学习的新方法。我们首先构建了一个理论因果框架，说明了现有的知识整合方法为何会在分布鲁棒目标上导致更差的性能。随后，我们展示了RIME能够同时整合这两种偏置，在干扰变量变化族的知情元学习场景中，于分布鲁棒目标下达到了最先进的性能。
英文摘要：
In settings where both spurious and causal predictors are available, standard neural networks trained under the objective of empirical risk minimization (ERM) with no additional inductive biases tend to have a dependence on a spurious feature. As a result, it is necessary to integrate additional inductive biases in order to guide the network toward generalizable hypotheses. Often these spurious features are shared across related tasks, such as estimating disease prognoses from image scans coming from different hospitals, making the challenge of generalization more difficult. In these settings, it is important that methods are able to integrate the proper inductive biases to generalize across both nuisance-varying families as well as task families. Motivated by this setting, we present RIME (Robustly Informed Meta lEarning), a new method for meta learning under the presence of both positive and negative inductive biases (what to learn and what not to learn). We first develop a theoretical causal framework showing why existing approaches at knowledge integration can lead to worse performance on distributionally robust objectives. We then show that RIME is able to simultaneously integrate both biases, reaching state of the art performance under distributionally robust objectives in informed meta-learning settings under nuisance-varying families.
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。
