论文标题
条件元学习的结构化预测
Structured Prediction for Conditional Meta-Learning
论文作者
论文摘要
基于优化的元学习的目的是在任务分布之间找到一个单个初始化，以加快学习新任务的过程。有条件的元学习寻求特定于任务的初始化，以更好地捕获复杂的任务分布并提高性能。但是，许多现有的有条件方法很难概括和缺乏理论保证。在这项工作中，我们通过结构化预测提出了有关条件元学习的新观点。我们得出任务自适应结构化元学习（TASML），这是一个原则性的框架，通过在目标任务上称量元培训数据来产生特定于任务的目标函数。我们的非参数方法是模型不可静止的方法，可以与现有的元学习方法结合使用以实现调理。从经验上讲，我们表明TASML提高了现有的元学习模型的性能，并优于基准数据集上的最新表现。
The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing conditional methods are difficult to generalize and lack theoretical guarantees. In this work, we propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions by weighing meta-training data on target tasks. Our non-parametric approach is model-agnostic and can be combined with existing meta-learning methods to achieve conditioning. Empirically, we show that TASML improves the performance of existing meta-learning models, and outperforms the state-of-the-art on benchmark datasets.
