Machine learning methods especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for training. In real-world applications, we often need to address sample shortage due to e.g., dynamic contexts with emerging prediction targets and costly sample annotation. Therefore, low-resource learning, which aims to learn robust prediction models with limited training samples, is now being widely investigated. Among all the low-resource learning studies, many prefer to utilize some auxiliary information in the form of Knowledge Graph (KG), which is becoming more and more popular for knowledge representation, to reduce the reliance on labeled samples. In this survey, we very comprehensively reviewed over 90 papers about KG-aware research for two major low-resource learning settings -- zero-shot learning (ZSL) where new classes for prediction have never appeared in training, and few-shot learning (FSL) where new classes for prediction have only a small number of labeled samples that are available. We first introduced the KGs used in ZSL and FSL studies as well as the existing and potential KG construction solutions, and then systematically categorized and summarized KG-aware ZSL and FSL methods, dividing them into different paradigms such as the mapping-based, the data augmentation, the propagation-based and the optimization-based. We next presented different applications, including not only KG augmented prediction tasks in Computer Vision and Natural Language Processing (e.g., image classification, visual question answering and knowledge extraction), but also tasks for KG curation (e.g., inductive KG completion), and some typical evaluation resources for each task. We eventually discussed some challenges and future directions on aspects such as new learning and reasoning paradigms, and the construction of high quality KGs.
翻译:机械学习方法,特别是深层神经网络取得了巨大成功,但其中许多国家往往依赖一些标签标注的培训样本。在现实世界应用中,我们常常需要解决由于以下原因导致的样本短缺问题:例如,动态环境,正在出现预测目标,抽样说明费用昂贵;因此,目前正在广泛调查低资源学习,目的是学习稳健的预测模型,培训样本有限;在所有低资源学习研究中,许多人倾向于使用一些辅助性信息,即知识图(KG),这种图正越来越流行,以减少对标签标定样本的依赖。在本次调查中,我们非常全面地审查了90多份关于KG-aware研究的论文,涉及两个主要的低资源学习环境 -- -- 零点学习(ZSL),在培训中从未出现新的预测课程,而很少有贴标签的样本。 在基于ZSL和FSL的研究中,我们首先将基于KSL的KG, 和FSL 的分类研究中所使用的KG, 以及现有的和潜在的建筑解决方案,然后系统分类和总结和总结KG-G-G-SL的视觉分析,最终的逻辑和模型分析, 各种模型,包括了K-G-G-G-SL的数据-SL