Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. However, a large number of meta-training tasks are still required for generalization to unseen tasks during meta-testing, which introduces a critical bottleneck for real-world problems that come with only few tasks, due to various reasons including the difficulty and cost of constructing tasks. Recently, several task augmentation methods have been proposed to tackle this issue using domain-specific knowledge to design augmentation techniques to densify the meta-training task distribution. However, such reliance on domain-specific knowledge renders these methods inapplicable to other domains. While Manifold Mixup based task augmentation methods are domain-agnostic, we empirically find them ineffective on non-image domains. To tackle these limitations, we propose a novel domain-agnostic task augmentation method, Meta-Interpolation, which utilizes expressive neural set functions to densify the meta-training task distribution using bilevel optimization. We empirically validate the efficacy of Meta-Interpolation on eight datasets spanning across various domains such as image classification, molecule property prediction, text classification and speech recognition. Experimentally, we show that Meta-Interpolation consistently outperforms all the relevant baselines. Theoretically, we prove that task interpolation with the set function regularizes the meta-learner to improve generalization.
翻译:元学习方法使机器学习系统能够利用相关任务的知识,适应新任务。然而,在元测试期间,仍需要大量的元培训任务,才能将常规任务推广到无形任务,这为现实世界问题带来了严重的瓶颈,由于各种原因,包括任务建设的困难和成本等,这些困难和成本等原因,这些困难和学习方法很少。最近,提出了几种任务增强方法来解决这一问题,利用特定领域知识设计增强技术,以缩小元培训任务分配的密度。然而,这种对特定领域知识的依赖使得这些方法不适用于其他领域。虽然基于曼尼化的混合任务增强方法具有域名性,但我们在经验上发现它们在非图像领域是无效的。为了克服这些限制,我们建议采用一种新的域名化任务增强方法,即元培训任务分配运用双级优化。我们通过经验验证元化集集对八个领域的数据集的功效,例如图像分类、分子财产预测、文本分类和正统化语音识别等。我们不断将模型化的模型化的模型化,显示我们不断的模型化的模型化的标准化任务。